© 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. 6-RES-JB
    11. 2706
    Prev
    Next
    INDEX
    Explanations

    statements regarding responses to requests or comments

    oai_token-act-pair · gpt-3.5-turbo

    references to comments and responses related to requests in a news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TABLE
    -0.76
    parts
    -0.73
    surv
    -0.66
     Thumbnails
    -0.65
    hab
    -0.65
    Less
    -0.61
    1920
    -0.60
    advant
    -0.59
    çľ
    -0.59
     intest
    -0.59
    POSITIVE LOGITS
     nor
    0.86
     spokeswoman
    0.80
     emailed
    0.80
     specifics
    0.76
     spokesman
    0.74
     inquiries
    0.72
     confir
    0.71
     spokesperson
    0.67
     pending
    0.67
     solicitor
    0.67
    Activations Density 0.304%

    No Known Activations