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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6749
    Prev
    Next
    INDEX
    Explanations

    references to ghosts or ghost-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    1.0%
    1053
    +0.14
    0.8%
    1101
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.18
    0.02
    1233
    +0.14
    0.02
    1691
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.54
    mm
    -0.64
    HasColumnType
    -0.64
    Архівовано
    -0.63
    addPreferredGap
    -0.61
    public
    -0.61
     PeEnEo
    -0.59
    Đặc
    -0.59
    glDelete
    -0.59
    Autoritní
    -0.58
    POSITIVE LOGITS
     ghost
    1.36
     Ghost
    1.29
     thut
    1.28
     saar
    1.23
     ghosts
    1.21
     jati
    1.19
    ghost
    1.19
    Ghost
    1.18
     ftu
    1.15
     Ghosts
    1.14
    Activations Density 0.049%

    No Known Activations