© 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. 2642
    Prev
    Next
    INDEX
    Explanations

    information related to specific scenarios or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "which" used to introduce clauses

    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
    dj
    -0.72
    soType
    -0.71
    redit
    -0.70
    marg
    -0.68
     defic
    -0.67
    Roll
    -0.67
    bang
    -0.65
    sc
    -0.65
    sci
    -0.64
    rene
    -0.64
    POSITIVE LOGITS
    soever
    1.07
    upon
    0.86
     case
    0.82
    kson
    0.73
     cases
    0.71
     guts
    0.70
     contestants
    0.68
     personalities
    0.67
    andom
    0.67
     they
    0.64
    Activations Density 0.036%

    No Known Activations