© 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. 6-RES-JB
    11. 5071
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating mistakes or misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.87
    edia
    -0.77
    prus
    -0.63
    earcher
    -0.62
    bsite
    -0.61
     nearest
    -0.60
    odore
    -0.60
    rique
    -0.60
     [|
    -0.60
    ellow
    -0.59
    POSITIVE LOGITS
     except
    1.03
    together
    0.96
     together
    0.90
     facets
    0.76
     toget
    0.75
     revolves
    0.73
     alike
    0.71
    opathic
    0.69
    oots
    0.68
    except
    0.66
    Activations Density 0.183%

    No Known Activations