© 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. 2-RES-JB
    6. 12935
    Prev
    Next
    INDEX
    Explanations

    dialogue lines specified by characters' names

    oai_token-act-pair · gpt-3.5-turbo

    dialogue and conversational interactions among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.83
    ilater
    -0.72
     innov
    -0.71
     upstream
    -0.69
     downstream
    -0.69
     Berman
    -0.68
    itionally
    -0.67
    lishes
    -0.67
    ospons
    -0.67
    é¾į
    -0.67
    POSITIVE LOGITS
     Weasley
    0.95
    âĶĢâĶĢ
    0.92
     Hermione
    0.91
     Jaune
    0.91
     Snape
    0.88
     princess
    0.88
     Dumbledore
    0.87
     grin
    0.85
     Pyrrha
    0.84
     Hogwarts
    0.83
    Activations Density 1.244%

    No Known Activations