© 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. 1-RES-JB
    11. 16841
    Prev
    Next
    INDEX
    Explanations

    words related to writing, such as "scribe," "transcribe," and "describe."

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "scribe" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fighting
    -0.70
    cgi
    -0.70
     HMS
    -0.67
    SUP
    -0.65
     Savannah
    -0.64
     domain
    -0.61
    arts
    -0.60
     OK
    -0.59
    ÃŁ
    -0.58
    �
    -0.58
    POSITIVE LOGITS
    ribe
    1.36
    ribing
    1.20
    ribes
    1.19
    ribed
    1.16
    riber
    1.14
     nostalg
    0.97
    xual
    0.91
     sugg
    0.89
    urally
    0.88
    rers
    0.82
    Activations Density 0.009%

    No Known Activations