© 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. 6-RES-JB
    11. 4467
    Prev
    Next
    INDEX
    Explanations

    the word 'something' or 'nothing'

    oai_token-act-pair · gpt-3.5-turbo

    references to uncertainty or general statements about conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipel
    -0.71
    aunder
    -0.68
     sidx
    -0.67
    mma
    -0.64
    essen
    -0.64
    iky
    -0.64
    ific
    -0.63
    inar
    -0.61
    habi
    -0.59
    ãĤ´ãĥ³
    -0.59
    POSITIVE LOGITS
     person
    0.68
     foreigners
    0.64
     unborn
    0.64
     disgruntled
    0.63
     persons
    0.61
     )))
    0.60
     fortun
    0.60
     discriminated
    0.59
     attacker
    0.59
     TAMADRA
    0.58
    Activations Density 0.368%

    No Known Activations