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. 11658
    Prev
    Next
    INDEX
    Explanations

    references to the team "Ravens."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Ravens" team

    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
    awaru
    -0.83
    unct
    -0.68
    trak
    -0.68
    olulu
    -0.68
    ahime
    -0.66
    employment
    -0.66
     Nicaragua
    -0.65
    rists
    -0.65
    akespe
    -0.64
    efficients
    -0.64
    POSITIVE LOGITS
     Ravens
    1.35
     Orioles
    1.11
    Raven
    0.90
    claw
    0.79
     Raiders
    0.76
     Raven
    0.74
    ettes
    0.71
     Colts
    0.68
     Bengals
    0.67
     Beasts
    0.66
    Activations Density 0.006%

    No Known Activations