© 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. 8-RES-JB
    11. 15191
    Prev
    Next
    INDEX
    Explanations

    words related to reflection or reflective activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reflection or reflective processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.79
    nut
    -0.79
    corn
    -0.76
    ccess
    -0.73
    ################
    -0.71
    ciating
    -0.67
    LOAD
    -0.66
    uga
    -0.65
    ESE
    -0.63
    ahime
    -0.62
    POSITIVE LOGITS
    ivity
    0.86
     sunlight
    0.85
    glass
    0.84
    ively
    0.83
    lection
    0.82
     reflection
    0.82
     reflections
    0.80
    lections
    0.80
     reflecting
    0.79
    ivities
    0.74
    Activations Density 0.041%

    No Known Activations