© 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. 2-RES-JB
    11. 785
    Prev
    Next
    INDEX
    Explanations

    the prefix "ob"

    oai_token-act-pair · gpt-4-turbo

    words related to oblique references or obstructed views

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "ob."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EngineDebug
    -0.91
     guiActiveUnfocused
    -0.84
    agne
    -0.81
    anwhile
    -0.78
    SEA
    -0.75
     Prosper
    -0.74
     Michaels
    -0.71
    REDACTED
    -0.70
    DragonMagazine
    -0.70
    terday
    -0.69
    POSITIVE LOGITS
    lique
    1.41
    livion
    1.09
    structed
    1.01
    ©¶æ
    1.01
    tains
    0.99
    amacare
    0.98
    eyed
    0.93
    itted
    0.92
    nox
    0.90
    acco
    0.89
    Activations Density 0.007%

    No Known Activations