© 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. 4-RES-JB
    11. 15635
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or places starting with "Ro" or "Ale" and ending with "well," "ovic," "ales," or "coe."

    oai_token-act-pair · gpt-3.5-turbo

    names and references to individuals or characters

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

    No Comments

    Negative Logits
    ulhu
    -0.83
    ACTED
    -0.82
    ecause
    -0.80
    Newsletter
    -0.77
    RIC
    -0.69
    Posts
    -0.68
    Anonymous
    -0.67
    ICLE
    -0.66
    channelAvailability
    -0.66
    aneers
    -0.64
    POSITIVE LOGITS
    issance
    0.74
    opol
    0.71
    oping
    0.68
    opal
    0.67
    vous
    0.67
    backer
    0.67
    ope
    0.67
    enz
    0.66
    afort
    0.66
     Ferdinand
    0.66
    Activations Density 0.080%

    No Known Activations