© 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. 11-RES-JB
    11. 7057
    Prev
    Next
    INDEX
    Explanations

    advice and related words

    oai_token-act-pair · gpt-3.5-turbo

    references to advice in various contexts

    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
    bang
    -0.72
    ophon
    -0.70
    BP
    -0.70
    WithNo
    -0.68
    chin
    -0.67
    Charges
    -0.67
    POSE
    -0.65
    dimension
    -0.63
    TF
    -0.63
    asts
    -0.63
    POSITIVE LOGITS
     advice
    1.00
     Advice
    0.94
     advised
    0.92
     advising
    0.91
     recommending
    0.87
     advise
    0.84
     given
    0.82
     counselor
    0.82
     counselors
    0.80
     glean
    0.77
    Activations Density 0.084%

    No Known Activations