© 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. 4-RES-JB
    11. 15285
    Prev
    Next
    INDEX
    Explanations

    contractions of "are not" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions and forms of denial

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

    No Comments

    Negative Logits
    ramid
    -0.70
    fox
    -0.66
    croft
    -0.66
     Mechdragon
    -0.64
    ochond
    -0.63
     PU
    -0.62
     Draw
    -0.61
     step
    -0.60
     duty
    -0.60
    owan
    -0.59
    POSITIVE LOGITS
    't
    1.25
    iting
    0.84
    ited
    0.83
    ajor
    0.82
    etsk
    0.77
    tyard
    0.76
    ates
    0.74
    tesy
    0.72
    geon
    0.72
    nel
    0.72
    Activations Density 0.056%

    No Known Activations