Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 512
    Prev
    Next
    INDEX
    Explanations

    information about reviews or evaluations, specifically related to products or media

    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
    2034
    +0.16
    0.5%
    382
    +0.15
    0.4%
    1535
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.16
    0.06
    1430
    +0.15
    0.03
    1445
    +0.10
    0.04
    Negative Logits
     unlaw
    -1.26
     affor
    -1.20
     impractica
    -1.18
     guarante
    -1.17
     unwarran
    -1.16
     disagre
    -1.16
     increa
    -1.16
     purcha
    -1.14
     maneu
    -1.14
     chrysler
    -1.11
    POSITIVE LOGITS
     Instead
    1.16
     instead
    1.14
    Instead
    1.09
    instead
    1.04
     but
    0.98
     But
    0.98
    but
    0.96
    But
    0.88
     However
    0.85
     Unfortunately
    0.80
    Activations Density 0.288%

    No Known Activations