© 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. 12547
    Prev
    Next
    INDEX
    Explanations

    mentions of specific users or profiles indicated by hashtags

    oai_token-act-pair · gpt-3.5-turbo

    hashtags and metrics related to social media activity

    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
     weap
    -0.68
    boro
    -0.64
     Wander
    -0.63
     Sov
    -0.62
    istani
    -0.61
    ahime
    -0.61
     Pilgrim
    -0.61
     Ortiz
    -0.60
     Fighters
    -0.60
     Deng
    -0.59
    POSITIVE LOGITS
    ########
    1.22
    ################################
    1.21
    ################
    1.01
    region
    0.94
    ###
    0.91
    ANN
    0.83
    interesting
    0.81
    why
    0.80
    !/
    0.78
    Delete
    0.75
    Activations Density 0.018%

    No Known Activations