© 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 EvalsExportsinterp-engineNEWAPI 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. 18415
    Prev
    Next
    INDEX
    Explanations

    names related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or unique names

    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
    atility
    -0.78
    sburg
    -0.73
     GER
    -0.73
    posts
    -0.66
     +++
    -0.65
    ulence
    -0.65
    Kings
    -0.64
     defect
    -0.64
    Mich
    -0.63
    HCR
    -0.63
    POSITIVE LOGITS
    oan
    1.15
    alyses
    1.13
    alyst
    1.07
    vernment
    0.91
    ecd
    0.88
    onga
    0.86
    oca
    0.82
    obal
    0.80
    cient
    0.79
    omen
    0.79
    Activations Density 0.021%

    No Known Activations