INDEX

Explanations

mentions of Pew Research

oai_token-act-pair · gpt-3.5-turbo

references to research studies and reports, particularly from the Pew Research Center

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ufact

-0.72

jriwal

-0.66

GBT

-0.65

Duc

-0.64

 Shim

-0.64

achev

-0.64

Nib

-0.63

 adul

-0.62

ionic

-0.62

ysis

-0.61

POSITIVE LOGITS

 Center

0.84

 Institute

0.69

 interviewing

0.67

lished

0.66

Center

0.66

itzer

0.64

 Foundation

0.64

leground

0.63

reports

0.63

 interviewed

0.62

Activations Density 0.075%

mentions of Pew Research

references to research studies and reports, particularly from the Pew Research Center

No Comments

No Known Activations