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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18923
    Prev
    Next
    INDEX
    Explanations

    email addresses and technical information like IP addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to user states and input/output data structures

    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
     reconc
    -0.74
    cffff
    -0.73
     ende
    -0.68
     tremend
    -0.67
    tin
    -0.66
    ministic
    -0.66
     mathemat
    -0.63
    aiman
    -0.63
    packing
    -0.63
     obser
    -0.60
    POSITIVE LOGITS
    estic
    0.86
    shire
    0.75
    tenance
    0.74
    reme
    0.74
     }}
    0.74
    ension
    0.73
    agne
    0.73
    bsite
    0.71
    acters
    0.71
    itime
    0.71
    Activations Density 0.027%

    No Known Activations