© 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. 9-RES-JB
    11. 1017
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to corporations

    oai_token-act-pair · gpt-3.5-turbo

    references to various corporations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boarding
    -0.72
    req
    -0.65
    syn
    -0.65
    STEM
    -0.64
    ymes
    -0.63
    ugg
    -0.63
    cknow
    -0.63
    joy
    -0.63
    Mic
    -0.63
    kit
    -0.63
    POSITIVE LOGITS
    ridor
    0.93
    enary
    0.92
    wide
    0.88
    oreal
    0.86
    redits
    0.82
    rane
    0.80
    emetery
    0.77
    orpor
    0.77
    ombat
    0.75
    ustom
    0.73
    Activations Density 0.059%

    No Known Activations