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. 15347
    Prev
    Next
    INDEX
    Explanations

    legal case names with the format of "Plaintiff v. Defendant" and related legal terms

    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
    394
    +0.10
    0.3%
    764
    +0.09
    0.3%
    1224
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.10
    0.02
    1203
    +0.09
    0.02
    520
    +0.09
    0.01
    Negative Logits
     mascarpone
    -0.59
    truction
    -0.58
     PROPOS
    -0.57
     tudom
    -0.55
     purée
    -0.55
    ecake
    -0.53
     pono
    -0.53
     taky
    -0.52
     lamborghini
    -0.51
     tupperware
    -0.51
    POSITIVE LOGITS
     déliv
    1.05
     vété
    1.04
     pério
    1.03
     précé
    1.02
     Secrétaire
    1.00
     confé
    0.99
     prédé
    0.99
     exclusivement
    0.99
     électron
    0.98
     noyau
    0.96
    Activations Density 0.061%

    No Known Activations