© 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. 21355
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or providing help or support

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "assistance" and related terminology

    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
    bish
    -0.76
    ross
    -0.73
    cott
    -0.73
    aval
    -0.73
    liness
    -0.72
    len
    -0.72
    trop
    -0.72
    leon
    -0.72
    gen
    -0.71
    osphere
    -0.71
    POSITIVE LOGITS
     assistance
    0.91
     package
    0.85
    ateral
    0.84
     counselors
    0.82
     counselor
    0.81
     Assistance
    0.78
     Package
    0.78
     Programs
    0.77
     afforded
    0.72
     packages
    0.72
    Activations Density 0.041%

    No Known Activations