© 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. 8-RES-JB
    11. 6246
    Prev
    Next
    INDEX
    Explanations

    personal pronouns or possessive pronouns associated with a sense of self

    oai_token-act-pair · gpt-3.5-turbo

    references to feelings and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Us
    -0.68
     themselves
    -0.66
     Their
    -0.63
    Their
    -0.61
     Plaint
    -0.59
     arsen
    -0.58
    idates
    -0.57
     us
    -0.57
     tariffs
    -0.56
     Diff
    -0.55
    POSITIVE LOGITS
     myself
    1.45
     blogging
    0.93
     my
    0.82
     typing
    0.72
     OCD
    0.71
    watching
    0.69
     researching
    0.68
     writing
    0.68
     personally
    0.66
    aido
    0.66
    Activations Density 1.006%

    No Known Activations