© 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. 2-RES-JB
    11. 24099
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the Harry Potter series

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and locations from the Harry Potter series

    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
    emp
    -0.76
    ip
    -0.70
    ayed
    -0.68
    ylene
    -0.68
    icking
    -0.67
    PsyNetMessage
    -0.67
    iq
    -0.67
    Machine
    -0.66
    imer
    -0.65
    oples
    -0.65
    POSITIVE LOGITS
     Dumbledore
    1.17
     Malfoy
    1.16
     Weasley
    1.02
     Voldemort
    1.01
     Hermione
    1.00
     Potter
    0.98
    umbledore
    0.97
     Snape
    0.95
    oldemort
    0.88
    uggle
    0.84
    Activations Density 0.023%

    No Known Activations