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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 18124
    Prev
    Next
    INDEX
    Explanations

    mentions of detectives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of detectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworld
    -0.90
    uled
    -0.83
    enes
    -0.82
    inst
    -0.79
    aston
    -0.79
    cius
    -0.79
    laus
    -0.79
    comes
    -0.77
    perm
    -0.77
    ais
    -0.76
    POSITIVE LOGITS
     Detective
    1.09
     detective
    1.05
     Detect
    0.90
     Grimoire
    0.89
     Constable
    0.84
     detectives
    0.82
    ective
    0.82
     Conan
    0.81
     Inspector
    0.80
     Pikachu
    0.76
    Activations Density 0.014%

    No Known Activations