© 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. 17118
    Prev
    Next
    INDEX
    Explanations

    terms related to photographic lenses and their features

    oai_token-act-pair · gpt-3.5-turbo

    words related to lenses and optics

    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
    BY
    -0.74
    lly
    -0.73
    TY
    -0.72
    pta
    -0.68
     quo
    -0.67
    ansom
    -0.65
    lishes
    -0.64
    onge
    -0.64
     Chatt
    -0.63
    currency
    -0.62
    POSITIVE LOGITS
     lenses
    1.10
     lens
    1.10
     flares
    1.07
     flare
    1.00
     Lens
    0.92
     Nikon
    0.87
    Lens
    0.86
    linger
    0.85
     glasses
    0.84
    ner
    0.84
    Activations Density 0.036%

    No Known Activations