© 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. 23357
    Prev
    Next
    INDEX
    Explanations

    iterations of the word "er" with a numerical significance attached to each

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix 'er'

    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
    ĸļ
    -0.76
    s
    -0.69
    ertodd
    -0.65
    urities
    -0.65
    raltar
    -0.64
    acebook
    -0.64
    UME
    -0.63
    ELS
    -0.63
    scl
    -0.63
    eenth
    -0.62
    POSITIVE LOGITS
    jee
    1.01
    lein
    0.96
    adish
    0.93
    idge
    0.91
    unning
    0.89
    aton
    0.87
    nery
    0.83
    rors
    0.82
    ror
    0.82
    cial
    0.81
    Activations Density 0.081%

    No Known Activations