© 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. 24163
    Prev
    Next
    INDEX
    Explanations

    details about event schedules and locations

    oai_token-act-pair · gpt-3.5-turbo

    event details, including timings and ticket information

    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
     discredited
    -0.82
    Wiki
    -0.81
     slime
    -0.78
    developed
    -0.73
     brute
    -0.72
     handwriting
    -0.72
     weakened
    -0.71
    weak
    -0.69
     biome
    -0.69
     muscle
    -0.69
    POSITIVE LOGITS
    Tickets
    1.16
     TBA
    0.99
     Tickets
    0.98
     Celebration
    0.95
     Doors
    0.90
     Warehouse
    0.86
     Indigo
    0.85
     Harbor
    0.85
     Holiday
    0.84
     Thurs
    0.83
    Activations Density 1.348%

    No Known Activations