© 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. 7-RES-JB
    11. 18707
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing or continued actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "continued" and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.81
    ramid
    -0.80
    arta
    -0.80
    ARP
    -0.77
    owitz
    -0.75
    IDS
    -0.75
    LCS
    -0.73
    erb
    -0.73
    verbs
    -0.72
    ĪĴ
    -0.72
    POSITIVE LOGITS
     existence
    1.06
     fascination
    0.95
     viability
    0.89
     evolution
    0.89
     absence
    0.88
     presence
    0.87
     reliance
    0.85
     relevance
    0.85
     obscurity
    0.84
     uninterrupted
    0.83
    Activations Density 0.024%

    No Known Activations