© 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. 10754
    Prev
    Next
    INDEX
    Explanations

    words related to obscuring or obfuscating information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to visibility and clarity, particularly those indicating obstruction or concealment

    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
    ties
    -0.92
    ty
    -0.74
    ng
    -0.73
    ube
    -0.72
    姫
    -0.70
    finder
    -0.68
    TAG
    -0.66
    Sit
    -0.66
    gs
    -0.63
    enger
    -0.63
    POSITIVE LOGITS
     silhou
    0.80
     obscured
    0.77
     poppy
    0.75
     EDITION
    0.73
    ĸļ
    0.73
     Mysteries
    0.70
     blurred
    0.70
     shading
    0.70
    xual
    0.70
     obsc
    0.70
    Activations Density 0.033%

    No Known Activations