© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 15194
    Prev
    Next
    INDEX
    Explanations

    instructions or information related to setting up accounts or memberships online

    oai_token-act-pair · gpt-3.5-turbo

    references to library cards and access to services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visc
    -0.74
     scandals
    -0.70
     smells
    -0.69
     blunt
    -0.69
    rums
    -0.69
     contrasts
    -0.67
     bleak
    -0.65
     stirring
    -0.64
     proverb
    -0.64
     interpretations
    -0.63
    POSITIVE LOGITS
     login
    1.27
     Login
    1.13
    login
    1.13
    ername
    1.10
    Login
    1.05
     password
    1.03
     unlock
    1.02
     Premium
    1.00
     Username
    1.00
     Password
    0.96
    Activations Density 0.646%

    No Known Activations