© 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. 0-RES-JB
    11. 1197
    Prev
    Next
    INDEX
    Explanations

    phrases related to first-person perspective in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to first-person perspectives and characters in narratives or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warn
    -0.61
     jun
    -0.61
     libraries
    -0.60
     stars
    -0.60
    UFF
    -0.59
     Fox
    -0.59
     curves
    -0.59
    UE
    -0.58
     embrace
    -0.58
     splend
    -0.58
    POSITIVE LOGITS
    person
    4.17
    Person
    2.44
    woman
    2.14
    pers
    1.93
     Person
    1.87
    people
    1.85
     person
    1.65
     PERSON
    1.57
    member
    1.50
    women
    1.44
    Activations Density 0.017%

    No Known Activations