© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 15184
    Prev
    Next
    INDEX
    Explanations

    phrases related to a sequence of actions or steps towards a goal

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    474
    +0.12
    0.4%
    196
    +0.12
    0.4%
    9
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.12
    0.07
    9
    +0.12
    0.05
    196
    +0.10
    0.05
    Negative Logits
     pymysql
    -0.83
     heapq
    -0.66
     psycopg
    -0.63
     pathlib
    -0.53
     hashlib
    -0.52
     Cerca
    -0.48
     pymongo
    -0.48
     zipfile
    -0.48
     smtplib
    -0.47
     Ngb
    -0.47
    POSITIVE LOGITS
    before
    0.84
     before
    0.84
     BEFORE
    0.82
     venuto
    0.74
    BEFORE
    0.74
     Before
    0.71
    Before
    0.68
     bago
    0.67
     sentito
    0.65
     antes
    0.61
    Activations Density 0.103%

    No Known Activations