INDEX

Explanations

words related to medical conditions or procedures

oai_token-act-pair · gpt-3.5-turbo

instances of the truncation "umm" and abbreviations related to unidentified formal entities

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

rett

-0.75

inia

-0.71

orius

-0.67

anco

-0.67

ikarp

-0.66

 Rossi

-0.64

utic

-0.63

raits

-0.63

 Colo

-0.62

 Abram

-0.61

POSITIVE LOGITS

swer

0.92

ãĥĦ

0.91

itor

0.86

odder

0.83

ipeg

0.82

merce

0.82

itri

0.81

itors

0.78

ulate

0.78

onymous

0.78

Activations Density 0.070%

words related to medical conditions or procedures

instances of the truncation "umm" and abbreviations related to unidentified formal entities

No Comments

No Known Activations