© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4185
    Prev
    Next
    INDEX
    Explanations

    phrases that are set off in quotation marks, typically indicating direct speech or verbatim material

    oai_token-act-pair · gpt-3.5-turbo

    contractions of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eal
    -0.84
    roit
    -0.78
    enth
    -0.69
    eals
    -0.68
    etts
    -0.67
    ares
    -0.66
    asured
    -0.65
    ear
    -0.65
    /+
    -0.63
    ||
    -0.63
    POSITIVE LOGITS
     nothing
    1.24
     been
    1.23
     gotta
    1.23
     plenty
    1.10
     no
    1.06
     always
    1.04
     definitely
    1.04
     nowhere
    1.02
     something
    1.01
     gonna
    0.99
    Activations Density 0.066%

    No Known Activations