INDEX

Explanations

words related to physical discomfort or distress

oai_token-act-pair · gpt-3.5-turbo

gerunds or present participles in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bal

-0.72

omet

-0.63

onso

-0.63

rgb

-0.62

isible

-0.62

ŀ

-0.62

Neg

-0.59

 Aerospace

-0.59

saf

-0.58

§

-0.58

POSITIVE LOGITS

 havoc

0.89

tons

0.88

redients

0.88

ulate

0.83

river

0.74

itcher

0.72

bilt

0.72

 noises

0.70

 Squid

0.69

stocks

0.69

Activations Density 0.125%

words related to physical discomfort or distress

gerunds or present participles in the text

No Comments

No Known Activations