© 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. 7-RES-JB
    11. 2210
    Prev
    Next
    INDEX
    Explanations

    technical terms, such as software and organization names

    oai_token-act-pair · gpt-3.5-turbo

    references to computer hacking and institutions, especially related to education or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staking
    -0.67
    Reviewer
    -0.66
    oaded
    -0.63
     tremend
    -0.61
    ancial
    -0.58
    awed
    -0.57
     strengths
    -0.56
    rather
    -0.56
    different
    -0.55
     sidew
    -0.55
    POSITIVE LOGITS
     âĵĺ
    1.05
     Extras
    0.73
     Miscellaneous
    0.70
     TBA
    0.69
     ----------------
    0.67
     (?,
    0.67
     Duo
    0.61
     Suite
    0.61
     Profile
    0.61
    ":["
    0.61
    Activations Density 0.452%

    No Known Activations