© 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. 4-RES-JB
    11. 13550
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name or term "Clothworks" or variations like "Clothworks Panel" and "Clothworkers."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Cl" that likely refer to a specific entity or category

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

    No Comments

    Negative Logits
    terday
    -0.78
     htt
    -0.70
    ãĤ®
    -0.69
    ãĥĨãĤ£
    -0.68
    ELL
    -0.68
    schild
    -0.67
    tumblr
    -0.67
    manship
    -0.66
    ãĥĦ
    -0.66
    shine
    -0.65
    POSITIVE LOGITS
    ipper
    1.21
    iff
    1.20
    iffs
    1.15
    oser
    1.13
    othes
    1.11
    utch
    1.10
    osures
    1.08
    amps
    1.05
    ients
    1.02
    osure
    1.02
    Activations Density 0.013%

    No Known Activations