© 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. 7609
    Prev
    Next
    INDEX
    Explanations

    instances where a subject or concept is introduced and elaborated on in a subsequent clause or sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events or significant moments

    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
    FF
    -0.58
    ideshow
    -0.58
     Survivors
    -0.58
     WARRANT
    -0.57
     misunderstanding
    -0.55
    oro
    -0.54
    Dynamic
    -0.53
     elapsed
    -0.53
     Casual
    -0.52
    oresc
    -0.52
    POSITIVE LOGITS
     surely
    0.76
     Name
    0.73
    name
    0.69
    apo
    0.68
     invariably
    0.68
    bern
    0.66
     preferably
    0.65
    Firstly
    0.64
    href
    0.63
    rase
    0.61
    Activations Density 0.225%

    No Known Activations