© 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. 4823
    Prev
    Next
    INDEX
    Explanations

    the central idea or main concept within a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating understanding or grasping concepts

    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
     unsolved
    -0.61
     hus
    -0.61
    ently
    -0.59
     inactive
    -0.57
    ril
    -0.55
     serv
    -0.55
     urgently
    -0.55
     fists
    -0.54
     scrub
    -0.53
     shel
    -0.53
    POSITIVE LOGITS
    ĸļ
    0.95
     enjoyment
    0.92
     benefit
    0.85
     benefits
    0.84
    rodu
    0.77
    ¿½
    0.76
    ))))
    0.75
    ģĸ
    0.75
     reap
    0.74
     opio
    0.73
    Activations Density 0.609%

    No Known Activations