© 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. 11-RES-JB
    11. 22666
    Prev
    Next
    INDEX
    Explanations

    phrases related to using the internet for educational and professional resources

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific token markers indicating the beginning or end of text segments

    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
    itia
    -0.73
    --+
    -0.63
    Cho
    -0.62
    ONSORED
    -0.62
    soever
    -0.62
    izes
    -0.62
    oe
    -0.62
    esar
    -0.61
    #$
    -0.61
    htar
    -0.60
    POSITIVE LOGITS
     sake
    1.62
     foreseeable
    1.42
     purposes
    1.27
     unin
    1.23
     longest
    1.16
     moment
    1.13
     meantime
    1.01
     past
    1.01
     duration
    1.00
     remainder
    0.99
    Activations Density 0.066%

    No Known Activations