© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 17113
    Prev
    Next
    INDEX
    Explanations

    texts related to providing and receiving advice

    oai_token-act-pair · gpt-3.5-turbo

    references to advice or guidance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FACE
    -0.68
    bang
    -0.66
    ches
    -0.63
    Jump
    -0.63
     Craw
    -0.63
    itol
    -0.63
    lock
    -0.62
    fare
    -0.61
     Alive
    -0.61
    chin
    -0.60
    POSITIVE LOGITS
     Advice
    1.07
     advising
    1.05
     advice
    1.03
     advise
    0.93
     advised
    0.89
    arial
    0.86
     recommending
    0.84
     advises
    0.78
     counselors
    0.77
     counselor
    0.76
    Activations Density 0.046%

    No Known Activations