© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11717
    Prev
    Next
    INDEX
    Explanations

    dates or specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to events or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appe
    -0.74
    ©¶æ
    -0.72
     placement
    -0.71
     tram
    -0.71
     confir
    -0.67
     ones
    -0.66
     totals
    -0.66
     deposits
    -0.65
     answ
    -0.64
     altern
    -0.64
    POSITIVE LOGITS
    ccording
    1.16
    Dear
    1.16
    Published
    1.14
    Advertisements
    1.12
    Introduction
    1.08
    Sometimes
    1.07
    Overview
    1.05
    When
    1.04
    If
    1.04
    Whether
    1.03
    Activations Density 0.385%

    No Known Activations