© 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. 6-RES-JB
    11. 21903
    Prev
    Next
    INDEX
    Explanations

    informal instances of meetings and appointments, both in general context and specific instances

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific days and actions related to meetings or interactions

    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
     replaced
    -0.71
     endif
    -0.69
     achieves
    -0.69
     survives
    -0.68
     dominates
    -0.67
     hits
    -0.67
     penal
    -0.61
     overtake
    -0.61
    Wr
    -0.61
    lins
    -0.61
    POSITIVE LOGITS
    rompt
    0.73
    oba
    0.72
    umbn
    0.69
    pport
    0.68
    assadors
    0.67
    Bed
    0.66
     Discord
    0.66
    robe
    0.64
    igslist
    0.63
     clandestine
    0.63
    Activations Density 0.381%

    No Known Activations