© 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. 10-RES-JB
    11. 24061
    Prev
    Next
    INDEX
    Explanations

    phrases related to being part of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "the" and references to problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     according
    -0.70
     Sections
    -0.69
    ptions
    -0.67
    atoon
    -0.67
    ants
    -0.67
     apart
    -0.67
    clips
    -0.67
    uba
    -0.67
    liam
    -0.66
    ãĥ»
    -0.66
    POSITIVE LOGITS
     equation
    1.28
     puzzle
    1.17
     solution
    1.01
     reason
    0.96
     continuum
    0.94
     rationale
    0.92
     ecosystem
    0.91
     arsenal
    0.90
     charm
    0.89
     mosaic
    0.88
    Activations Density 0.193%

    No Known Activations