© 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. 17734
    Prev
    Next
    INDEX
    Explanations

    words related to changes or modifications

    oai_token-act-pair · gpt-3.5-turbo

    references to significant alterations or adjustments in various contexts

    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
    amina
    -0.78
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.72
     AFB
    -0.72
    xious
    -0.69
     DRAGON
    -0.68
    ECD
    -0.67
    Äĩ
    -0.67
    ZE
    -0.67
    BILITY
    -0.67
    âĸ¬
    -0.66
    POSITIVE LOGITS
     effected
    0.91
    atile
    0.90
     wrought
    0.86
    hift
    0.85
    ettings
    0.83
    uits
    0.83
    ĸļ
    0.82
    oodoo
    0.81
    undown
    0.79
    ilver
    0.77
    Activations Density 0.023%

    No Known Activations