© 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. 21265
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and data

    oai_token-act-pair · gpt-3.5-turbo

    references to data distribution and digital media formats

    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
     Norris
    -0.73
     Ital
    -0.72
     Ki
    -0.70
    ofi
    -0.65
     laure
    -0.65
     Hai
    -0.64
     Ellis
    -0.64
    chwitz
    -0.64
     Kenny
    -0.64
    oru
    -0.64
    POSITIVE LOGITS
    based
    1.19
    driven
    1.17
    centric
    1.09
    related
    1.08
    mediated
    1.05
    derived
    1.04
    sav
    1.03
    generated
    1.02
    induced
    1.01
    intensive
    1.00
    Activations Density 0.106%

    No Known Activations