© 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. 4-RES-JB
    11. 8566
    Prev
    Next
    INDEX
    Explanations

    words related to bars and restaurants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bars and related establishments

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

    No Comments

    Negative Logits
    7601
    -0.71
    ãĤ¯
    -0.70
     genome
    -0.68
    åĬ
    -0.68
     captcha
    -0.64
     FIA
    -0.64
     declass
    -0.64
     Species
    -0.63
     Documents
    -0.61
     scientifically
    -0.61
    POSITIVE LOGITS
     frequ
    1.03
    itone
    0.98
     Royale
    0.94
    rooms
    0.93
    keep
    0.90
    bers
    0.88
    becue
    0.88
     café
    0.85
    room
    0.85
     catering
    0.83
    Activations Density 0.068%

    No Known Activations