© 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. 22581
    Prev
    Next
    INDEX
    Explanations

    phrases expressing existence or presence of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the words "there" and "here" indicating presence or location

    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
    ONSORED
    -0.76
    ãĥ£
    -0.73
    ãĥ¼ãĥĨ
    -0.72
    ãĥ¯ãĥ³
    -0.71
     actionGroup
    -0.71
    ORPG
    -0.70
     Regions
    -0.66
    è¦ļéĨĴ
    -0.62
    Recent
    -0.62
    864
    -0.61
    POSITIVE LOGITS
     ya
    1.23
    's
    1.15
     goes
    1.11
     ain
    0.98
     comes
    0.96
     you
    0.93
    upon
    0.91
    'll
    0.89
     Goes
    0.89
     we
    0.86
    Activations Density 0.101%

    No Known Activations