© 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. 3019
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures or components

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to tangible objects and structures

    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
    \\\\\\\\
    -0.89
    atalie
    -0.59
    DonaldTrump
    -0.59
    Motion
    -0.58
     Ventures
    -0.58
     Recomm
    -0.58
    ALLY
    -0.57
    Attempts
    -0.57
    -+-+
    -0.57
     Disorder
    -0.57
    POSITIVE LOGITS
     themselves
    1.23
    cape
    1.21
    etter
    1.14
    etting
    1.10
    mith
    1.07
    heet
    1.05
    linger
    1.05
    hip
    1.02
    hift
    0.98
    pace
    0.96
    Activations Density 0.445%

    No Known Activations