© 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. 9-RES-JB
    11. 2652
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating a portion or aspect of a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to parts of something or sectioning within a larger context

    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
     clipboard
    -0.69
     happiest
    -0.67
     slightest
    -0.67
     NEXT
    -0.63
     nodd
    -0.62
     Commissioners
    -0.61
     hawk
    -0.60
     favourite
    -0.59
     Keen
    -0.58
     LEVEL
    -0.56
    POSITIVE LOGITS
     thanks
    0.70
    REDACTED
    0.67
    urer
    0.66
    lie
    0.66
     attributable
    0.65
    spring
    0.64
     due
    0.63
     guiActiveUn
    0.63
    meal
    0.62
     because
    0.62
    Activations Density 0.036%

    No Known Activations