© 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. 9-RES-JB
    11. 2565
    Prev
    Next
    INDEX
    Explanations

    phrases related to appointments or selections of individuals for certain roles or tasks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Avlich" or references to specific players' performances

    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
     Rect
    -0.61
     typed
    -0.59
     indicative
    -0.58
     CLSID
    -0.57
     continual
    -0.56
     prevailing
    -0.56
     changing
    -0.56
     toile
    -0.56
    LOAD
    -0.56
    backer
    -0.55
    POSITIVE LOGITS
    irus
    1.26
    irtual
    1.15
    enture
    1.14
    ilion
    1.12
    arro
    1.12
    oided
    1.12
    ocado
    1.08
    oice
    1.08
    augh
    1.03
    atars
    1.03
    Activations Density 0.041%

    No Known Activations