© 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. 12808
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering or needing help

    oai_token-act-pair · gpt-3.5-turbo

    references to needing help or assistance

    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
    itect
    -0.75
     Democr
    -0.65
    azar
    -0.65
    atom
    -0.64
    imore
    -0.63
    querade
    -0.60
    ð
    -0.60
     Seym
    -0.60
    pire
    -0.59
    ignore
    -0.58
    POSITIVE LOGITS
    lessly
    1.43
     assistance
    1.27
     help
    1.19
     rescuing
    1.08
     reminding
    1.01
     repairs
    0.98
     clarification
    0.97
     reinforcements
    0.96
     advice
    0.95
     HELP
    0.92
    Activations Density 0.082%

    No Known Activations