Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5004
    Prev
    Next
    INDEX
    Explanations

    words related to causing negative effects or consequences

    oai_token-act-pair · gpt-3.5-turbo

    words related to separation or detachment

    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
    ortment
    -0.87
    ingham
    -0.78
    tyard
    -0.75
    eday
    -0.75
    umbers
    -0.73
    ellation
    -0.72
    ffield
    -0.71
    acca
    -0.71
    acci
    -0.70
    esame
    -0.69
    POSITIVE LOGITS
     Syndrome
    0.73
     barriers
    0.71
     demons
    0.69
     charms
    0.67
     Defeat
    0.67
     Territories
    0.66
     threats
    0.66
     enemies
    0.66
     stares
    0.66
     Enemy
    0.65
    Activations Density 0.072%

    No Known Activations