© 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. 6-RES-JB
    11. 18478
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to things happening or existing in the future

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future events or expectations

    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
    required
    -0.85
    lua
    -0.80
    cell
    -0.78
    orno
    -0.76
    pmwiki
    -0.75
    atto
    -0.75
    vacc
    -0.75
    wrapper
    -0.72
     sqor
    -0.72
    zee
    -0.72
    POSITIVE LOGITS
     undone
    0.99
     forth
    0.85
     rid
    0.75
    LLOW
    0.71
     attractions
    0.71
     WRITE
    0.70
     hereafter
    0.69
     alive
    0.68
     together
    0.68
     ashore
    0.67
    Activations Density 0.047%

    No Known Activations