© 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. 7-RES-JB
    11. 2043
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions carried out by multiple parties

    oai_token-act-pair · gpt-3.5-turbo

    instances of active or passive involvement of multiple subjects in various actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.63
    die
    -0.63
     Cree
    -0.63
     realization
    -0.61
    oken
    -0.60
     Riding
    -0.60
    Joined
    -0.59
    imeo
    -0.59
     Soda
    -0.59
     Dome
    -0.59
    POSITIVE LOGITS
     incarcer
    0.95
     awarding
    0.95
     assigning
    0.84
    intendent
    0.81
     jails
    0.81
     arresting
    0.80
    arantine
    0.80
     imprison
    0.80
     prosecuting
    0.79
     appoint
    0.79
    Activations Density 0.963%

    No Known Activations