© 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. 6-RES-JB
    6. 2783
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement or progression from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating transitions or movements between different states or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hair
    -0.67
     echoed
    -0.64
     shone
    -0.63
     breaks
    -0.63
     applies
    -0.63
    irez
    -0.62
     steered
    -0.62
    tek
    -0.61
    airy
    -0.61
     swung
    -0.60
    POSITIVE LOGITS
    asted
    0.87
    pless
    0.81
     fulfill
    0.79
    pload
    0.79
     fulfil
    0.78
     eliminate
    0.77
     minimize
    0.75
     infinity
    0.74
     conserve
    0.73
    iling
    0.72
    Activations Density 0.090%

    No Known Activations