© 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. 9-RES-JB
    11. 4224
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and actions in past tense

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unless
    -0.82
    ahime
    -0.69
    %.
    -0.67
    except
    -0.67
    WF
    -0.67
    .}
    -0.66
    ©¶æ¥µ
    -0.65
     unless
    -0.64
    bys
    -0.63
    ansk
    -0.62
    POSITIVE LOGITS
     last
    0.70
     hes
    0.60
     parting
    0.58
     announcing
    0.53
     landfall
    0.53
     puberty
    0.52
     inquire
    0.52
     timeout
    0.51
     finally
    0.51
     final
    0.51
    Activations Density 0.344%

    No Known Activations