© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7537
    Prev
    Next
    INDEX
    Explanations

    phrases where the text discusses the continuation or progression of a previous topic or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate progression or continuation of a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ullah
    -0.72
    ipation
    -0.60
    ateurs
    -0.59
    alis
    -0.58
    eers
    -0.57
     screens
    -0.56
    cape
    -0.56
    lake
    -0.55
     schedules
    -0.55
    icio
    -0.54
    POSITIVE LOGITS
    verning
    0.92
    ggle
    0.88
     overboard
    0.88
    vt
    0.85
    lems
    0.83
    along
    0.82
     forth
    0.76
     deeper
    0.76
    ffer
    0.75
     farther
    0.74
    Activations Density 0.091%

    No Known Activations