Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 12372
    Prev
    Next
    INDEX
    Explanations

    locations or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to personal identity and demographic characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disappear
    -0.72
     mockery
    -0.72
     vanish
    -0.68
     indefinitely
    -0.68
     waivers
    -0.68
     executions
    -0.64
     promptly
    -0.64
     virtues
    -0.63
     amenities
    -0.63
     substitution
    -0.62
    POSITIVE LOGITS
    strong
    0.80
     believer
    0.74
    veland
    0.73
    ecided
    0.70
     lucky
    0.68
    esty
    0.68
    uci
    0.66
     "$:/
    0.65
     privileged
    0.64
    blogspot
    0.64
    Activations Density 0.359%

    No Known Activations