© 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. 7-RES-JB
    11. 8756
    Prev
    Next
    INDEX
    Explanations

    adjectives with the prefix "un-" and verbs with the suffix "-ed" to indicate a lack of restriction or control

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "unfettered" and its variations, as well as associated concepts of freedom or lack of restriction

    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
    udeb
    -0.91
    enegger
    -0.73
    vertisement
    -0.68
    bourg
    -0.66
     estab
    -0.64
    ods
    -0.62
     acron
    -0.61
    utherland
    -0.61
    Clar
    -0.60
    utra
    -0.60
    POSITIVE LOGITS
     Wonderland
    0.71
    ibilities
    0.69
    iate
    0.68
    angular
    0.68
    ly
    0.66
     possessions
    0.65
    aneous
    0.65
    adoes
    0.64
     access
    0.64
    aneously
    0.64
    Activations Density 0.110%

    No Known Activations