© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2563
    Prev
    Next
    INDEX
    Explanations

    phrases related to helping someone with a task or chore

    oai_token-act-pair · gpt-3.5-turbo

    instances of helping or aiding others, particularly in the context of moving or assisting acquaintances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Daly
    -0.84
     Brach
    -0.83
     Deborah
    -0.77
    ihar
    -0.76
    Bon
    -0.76
    Bey
    -0.75
    Beta
    -0.75
     Bucc
    -0.75
    UTH
    -0.73
     Bland
    -0.72
    POSITIVE LOGITS
    move
    1.89
     move
    1.82
     Moving
    1.71
     Move
    1.70
    Move
    1.70
     moved
    1.69
     moving
    1.68
     moves
    1.61
     relocation
    1.61
    Moving
    1.61
    Activations Density 0.314%

    No Known Activations