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. 10072
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ghost" in various contexts

    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
    1053
    +0.15
    0.6%
    577
    +0.11
    0.4%
    528
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.15
    0.02
    1035
    +0.11
    0.02
    1233
    +0.11
    0.02
    Negative Logits
     PeEnEo
    -0.50
    Economía
    -0.49
    addPreferredGap
    -0.47
    Дереккөздер
    -0.46
    uncios
    -0.45
     Purdy
    -0.44
    ագրություններ
    -0.43
    marginVertical
    -0.42
    ppur
    -0.42
    bardier
    -0.41
    POSITIVE LOGITS
     ghost
    1.36
     Ghost
    1.24
     ghosts
    1.23
    ghost
    1.19
    Ghost
    1.16
     Ghosts
    1.10
    Ghosts
    0.98
     ghostly
    0.84
     haunted
    0.77
     haunt
    0.77
    Activations Density 0.099%

    No Known Activations