© 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. 21226
    Prev
    Next
    INDEX
    Explanations

    complaints or negative feedback

    oai_token-act-pair · gpt-3.5-turbo

    complaints about the costs and difficulties associated with luxury items or experiences

    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
    etheless
    -1.01
     sqor
    -0.72
     nonetheless
    -0.71
     GOODMAN
    -0.70
     conclud
    -0.70
    ensing
    -0.66
    amination
    -0.65
     acknowledgment
    -0.65
    ebin
    -0.65
    rontal
    -0.64
    POSITIVE LOGITS
     sucks
    1.18
     blah
    1.03
     crappy
    0.99
     crap
    0.94
     shitty
    0.93
     suck
    0.93
     useless
    0.89
     ruining
    0.88
     lazy
    0.86
     boring
    0.86
    Activations Density 0.606%

    No Known Activations