© 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. 0-RES-JB
    11. 6391
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inspection and scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JP
    -0.65
     ransom
    -0.63
     GF
    -0.63
     halves
    -0.61
     clen
    -0.60
     translation
    -0.59
     parted
    -0.59
     Dam
    -0.58
     dam
    -0.58
     gum
    -0.57
    POSITIVE LOGITS
    spect
    4.80
    spection
    2.60
    spective
    2.19
    Spect
    2.06
     Spect
    1.46
    pect
    1.30
    strument
    1.27
    gressive
    1.24
     Spectrum
    1.22
    ventory
    1.19
    Activations Density 0.022%

    No Known Activations