© 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. 4-RES-JB
    11. 1611
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perception or judgment about situations

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

    No Comments

    Negative Logits
    oning
    -0.80
    ricular
    -0.76
    ufact
    -0.70
    ilts
    -0.69
    atching
    -0.68
    estern
    -0.68
    rouse
    -0.65
    ilar
    -0.64
    ework
    -0.64
    shaw
    -0.64
    POSITIVE LOGITS
    rils
    0.78
    nir
    0.73
     contrad
    0.71
     plaus
    0.70
     likely
    0.70
     unlikely
    0.69
     omin
    0.67
     awfully
    0.67
    ģ«
    0.67
    Ĥİ
    0.67
    Activations Density 0.054%

    No Known Activations