© 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. 1-RES-JB
    11. 24174
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating legal allegations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal claims or statements of assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perm
    -0.79
    ammy
    -0.76
    aa
    -0.71
    talk
    -0.68
    perty
    -0.67
    ots
    -0.67
    oppy
    -0.67
    onen
    -0.66
    ggies
    -0.64
    ajo
    -0.62
    POSITIVE LOGITS
     alleges
    1.26
     allege
    1.03
     alleging
    1.00
     allegations
    0.98
     accuses
    0.95
     accusing
    0.88
     denies
    0.85
     accuse
    0.83
     accusations
    0.81
     accuser
    0.80
    Activations Density 0.009%

    No Known Activations