© 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. 11-RES-JB
    11. 10156
    Prev
    Next
    INDEX
    Explanations

    phrases related to different job positions and roles

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various professions or roles people have held

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayers
    -0.84
    akings
    -0.82
    osaurs
    -0.74
    NetMessage
    -0.73
    urrencies
    -0.73
    tons
    -0.71
    \":
    -0.71
    Known
    -0.70
    Ö¼
    -0.69
    tarians
    -0.68
    POSITIVE LOGITS
     liaison
    1.37
     consultant
    1.28
     advisor
    1.23
     translator
    1.22
     interpreter
    1.21
     adviser
    1.21
     informant
    1.18
     assistant
    1.18
     counselor
    1.15
     tutor
    1.14
    Activations Density 0.196%

    No Known Activations