© 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. 14740
    Prev
    Next
    INDEX
    Explanations

    words related to age or years

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ag" and its variations

    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
     Hurricanes
    -0.83
    éĹĺ
    -0.77
     Jenner
    -0.73
     Unloaded
    -0.71
    OCK
    -0.70
    ãĥĥãĤ¯
    -0.69
     Visitors
    -0.66
     Lumpur
    -0.66
     Petroleum
    -0.64
    pmwiki
    -0.63
    POSITIVE LOGITS
    nostic
    1.21
    irlf
    0.96
    encer
    0.93
    raf
    0.93
    oras
    0.93
    rade
    0.90
    anth
    0.89
    ri
    0.88
    sty
    0.88
    raphic
    0.88
    Activations Density 0.008%

    No Known Activations