© 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. 7-RES-JB
    11. 11628
    Prev
    Next
    INDEX
    Explanations

    instances of someone pointing something out

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the act of pointing out or making observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wake
    -0.92
    hei
    -0.83
    asus
    -0.71
    isode
    -0.70
    ascus
    -0.70
    soever
    -0.69
    ogue
    -0.68
    catentry
    -0.68
     confir
    -0.67
     experien
    -0.66
    POSITIVE LOGITS
     inconsistencies
    0.81
     contradictions
    0.79
     how
    0.78
     loopholes
    0.77
     flaws
    0.75
     discrepancies
    0.72
    pad
    0.71
    wards
    0.69
     deductions
    0.68
    olph
    0.68
    Activations Density 0.030%

    No Known Activations