© 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. 0-RES-JB
    11. 16926
    Prev
    Next
    INDEX
    Explanations

    references to messages or texts within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to "text" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.83
    erves
    -0.77
    士
    -0.73
    irk
    -0.72
     borne
    -0.70
    ajor
    -0.67
    apo
    -0.65
    shed
    -0.65
    asin
    -0.65
    arthy
    -0.65
    POSITIVE LOGITS
     text
    3.71
     texts
    2.73
     Text
    2.52
    text
    2.49
    Text
    2.32
     TEXT
    2.13
    TEXT
    1.71
     textual
    1.67
     texting
    1.65
     texted
    1.44
    Activations Density 0.019%

    No Known Activations