© 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. 3927
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarification or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing opinions or beliefs

    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
    artney
    -0.70
    izoph
    -0.64
    ifice
    -0.60
    ainer
    -0.60
    icidal
    -0.60
     substrate
    -0.59
     lif
    -0.58
    irlf
    -0.57
     spawn
    -0.57
    orum
    -0.56
    POSITIVE LOGITS
     myself
    1.12
    xtap
    0.77
     personally
    0.68
     congr
    0.67
     unres
    0.67
     fortunate
    0.66
    saw
    0.66
     gladly
    0.63
    Ļ½
    0.63
    poke
    0.63
    Activations Density 0.470%

    No Known Activations