© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11452
    Prev
    Next
    INDEX
    Explanations

    phrases relating to ratings, possibly reviews, movies, and other types of content, identified by the presence of "PG" or "PG" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific rating system for films or media content

    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
    advert
    -0.75
     Ic
    -0.74
    joined
    -0.68
     Horizons
    -0.68
    self
    -0.64
    framework
    -0.64
    fact
    -0.62
    deals
    -0.60
    kers
    -0.59
    izen
    -0.59
    POSITIVE LOGITS
    PG
    1.09
    PI
    0.95
    RAM
    0.94
    PAR
    0.87
    Ps
    0.84
    PU
    0.81
    HT
    0.81
    eln
    0.81
    TA
    0.80
    PF
    0.80
    Activations Density 0.005%

    No Known Activations