© 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. 4-RES-JB
    11. 14790
    Prev
    Next
    INDEX
    Explanations

    the word "host" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or collections of items or subjects

    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
    prints
    -0.78
    âĵĺ
    -0.74
    anium
    -0.67
     Tycoon
    -0.67
    agate
    -0.67
    hester
    -0.66
    ses
    -0.65
    appers
    -0.64
    akings
    -0.63
    doms
    -0.62
    POSITIVE LOGITS
    dozen
    0.82
     amount
    0.73
     array
    0.65
    etheless
    0.65
    ©¶æ¥µ
    0.64
    ographically
    0.61
     dozen
    0.60
     degree
    0.59
     series
    0.57
     AW
    0.57
    Activations Density 0.135%

    No Known Activations