© 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. 1050
    Prev
    Next
    INDEX
    Explanations

    I am unable to provide a summary for Neuron 4 at this time. There seems to be a technical issue with the data

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of merits or virtues

    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
    yss
    -0.72
    shr
    -0.69
    eden
    -0.69
    URA
    -0.68
    quickShipAvailable
    -0.64
    gdala
    -0.63
    alien
    -0.61
     hr
    -0.61
    overed
    -0.61
    zie
    -0.61
    POSITIVE LOGITS
     merits
    1.41
     merit
    0.98
    manship
    0.90
     judgement
    0.89
     judgments
    0.82
    avorite
    0.81
    aint
    0.77
    folios
    0.75
     plaus
    0.73
     guiActiveUn
    0.73
    Activations Density 0.010%

    No Known Activations