© 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. 10-RES-JB
    11. 14150
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing or receiving help or assistance

    oai_token-act-pair · gpt-3.5-turbo

    references to support and aid, particularly in collaborative or assistive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obos
    -0.58
    adesh
    -0.56
     segreg
    -0.54
    apor
    -0.53
    apons
    -0.53
    eeks
    -0.53
    gress
    -0.52
     Bridges
    -0.51
     aspir
    -0.51
     PTS
    -0.51
    POSITIVE LOGITS
     of
    0.95
     assistance
    0.81
     thereof
    0.79
     conn
    0.78
     supplied
    0.73
     provided
    0.71
    ij
    0.70
     Of
    0.68
     help
    0.67
     aid
    0.67
    Activations Density 0.122%

    No Known Activations