© 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. 7-RES-JB
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    names and titles that include a combination of a first name and a last name with a hyphen between them

    oai_token-act-pair · gpt-3.5-turbo

    references to South Korean political figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bounce
    -0.75
     contextual
    -0.69
     calibration
    -0.68
     steer
    -0.68
    kefeller
    -0.66
     subtract
    -0.66
     disrupted
    -0.66
     sticking
    -0.65
     underscore
    -0.64
     exec
    -0.63
    POSITIVE LOGITS
    sama
    1.10
    san
    1.10
    chan
    1.09
    Lago
    1.09
    kun
    1.06
    Sa
    1.05
    La
    0.97
    Pierre
    0.97
    sha
    0.95
    Lo
    0.95
    Activations Density 0.060%

    No Known Activations