© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7771
    Prev
    Next
    INDEX
    Explanations

    commands or actions related to programming or digital tasks

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to actions or commands that involve decision-making or modifications

    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
    brew
    -0.75
    mot
    -0.63
    mb
    -0.61
    wagen
    -0.61
    heddar
    -0.60
    ©¶æ
    -0.60
    ws
    -0.59
    Wire
    -0.59
    timer
    -0.59
    design
    -0.58
    POSITIVE LOGITS
    ificate
    0.77
     anything
    0.67
    enance
    0.66
     ANY
    0.65
    igate
    0.65
    л
    0.65
     DPR
    0.65
     any
    0.65
     them
    0.64
     Submit
    0.63
    Activations Density 0.164%

    No Known Activations