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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14684
    Prev
    Next
    INDEX
    Explanations

    actions related to signing up or subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to signing up or subscribing

    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
     nerv
    -0.78
    ooked
    -0.77
    ĸļ
    -0.73
    »Ĵ
    -0.72
    @#&
    -0.69
    olt
    -0.68
    ETHOD
    -0.67
    UTE
    -0.65
    ww
    -0.64
    70710
    -0.63
    POSITIVE LOGITS
     Sign
    1.22
    atories
    1.21
    ificantly
    1.19
    Sign
    1.14
    ific
    1.11
    sign
    1.09
    atures
    1.03
    ificant
    1.02
     sign
    0.96
    posts
    0.94
    Activations Density 0.014%

    No Known Activations