© 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. 3-RES-JB
    11. 7087
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day" (e.g., "Feb 9")

    oai_token-act-pair · gpt-3.5-turbo

    dates referencing February 9th and 10th

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
    éĹĺ
    -0.79
    ablishment
    -0.63
    schild
    -0.63
    é¾į
    -0.61
    ij士
    -0.61
    estern
    -0.60
    ollow
    -0.59
    akens
    -0.58
    ophers
    -0.58
    POSITIVE LOGITS
    uary
    0.97
    ruary
    0.94
    Feb
    0.94
     Feb
    0.91
    omore
    0.88
    Aug
    0.87
    bris
    0.84
    nd
    0.83
     2019
    0.82
    vier
    0.81
    Activations Density 0.007%

    No Known Activations