© 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. 8-RES-JB
    11. 2651
    Prev
    Next
    INDEX
    Explanations

    words related to structure or formation

    oai_token-act-pair · gpt-3.5-turbo

    variations of the root word "form."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BLIC
    -0.71
    Fr
    -0.66
     Fas
    -0.65
    lder
    -0.63
    prints
    -0.63
     Fey
    -0.62
    print
    -0.62
     frag
    -0.60
    adena
    -0.60
     FTA
    -0.59
    POSITIVE LOGITS
    yss
    1.05
    etheus
    0.95
    orph
    0.92
    pter
    0.86
    s
    0.85
    ous
    0.84
    ously
    0.83
    orm
    0.82
    orously
    0.82
    orthy
    0.80
    Activations Density 0.040%

    No Known Activations