© 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. 4007
    Prev
    Next
    INDEX
    Explanations

    words related to being illogical and unfair, as well as legal terms related to violations of rights

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms related to irrationality and unreasonableness

    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
    illes
    -0.80
    erville
    -0.79
    ebus
    -0.77
    ournals
    -0.77
    llan
    -0.75
    ription
    -0.75
    eor
    -0.74
    aign
    -0.73
    ivia
    -0.72
    icion
    -0.71
    POSITIVE LOGITS
     impulses
    0.81
    GBT
    0.81
     irrational
    0.79
     impulse
    0.75
     gratification
    0.74
     unfounded
    0.73
     whims
    0.70
     delays
    0.70
     accommodation
    0.69
     expectations
    0.69
    Activations Density 0.016%

    No Known Activations