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

    Neuronpedia

    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. 6-RES-JB
    11. 13474
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities or legal actions

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of the word "has" in various contexts

    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
    eem
    -0.73
     behold
    -0.67
    etting
    -0.66
    oppable
    -0.65
    ickle
    -0.63
    seless
    -0.62
    inkle
    -0.60
    —-
    -0.60
    atically
    -0.60
    uggle
    -0.59
    POSITIVE LOGITS
     been
    1.38
    been
    1.19
     undergone
    1.11
     emerged
    1.09
     become
    1.04
     begun
    1.00
     survived
    0.93
     surfaced
    0.90
     criticised
    0.90
     arisen
    0.89
    Activations Density 0.281%

    No Known Activations