© 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. 6503
    Prev
    Next
    INDEX
    Explanations

    expressions or clauses indicating a contrast or an addition to a previous statement

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the phrase "after all."

    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
    alysed
    -0.74
    MpServer
    -0.74
    SN
    -0.69
    pec
    -0.68
    Near
    -0.67
    Alias
    -0.60
    xon
    -0.59
    Repeat
    -0.59
    min
    -0.58
     vari
    -0.57
    POSITIVE LOGITS
     why
    0.82
    nob
    0.78
     nobody
    0.75
     there
    0.74
     imagine
    0.73
     wouldn
    0.71
    tons
    0.71
     unlike
    0.71
     isn
    0.70
     suppose
    0.70
    Activations Density 0.099%

    No Known Activations