© 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. 11-RES-JB
    11. 9929
    Prev
    Next
    INDEX
    Explanations

    locations or positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a vague or unspecified location in time or space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raid
    -0.78
    ombat
    -0.73
    ii
    -0.71
    iger
    -0.70
    andel
    -0.69
    ortex
    -0.65
    iframe
    -0.65
    icer
    -0.64
    atto
    -0.64
    eri
    -0.63
    POSITIVE LOGITS
     between
    1.13
     else
    1.07
    between
    0.98
     along
    0.96
     around
    0.93
    Else
    0.89
     somew
    0.88
     underneath
    0.84
     downstream
    0.84
     beneath
    0.82
    Activations Density 0.046%

    No Known Activations