INDEX

Explanations

phrases related to physically impacting or reaching a target

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "hit" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

pires

-0.91

agin

-0.75

inent

-0.71

æ©Ł

-0.70

ç«

-0.68

UTH

-0.66

cia

-0.61

¥µ

-0.60

algia

-0.60

otive

-0.59

POSITIVE LOGITS

ched

1.23

ches

0.93

boxes

0.86

ted

0.82

tle

0.81

chens

0.79

achi

0.79

box

0.78

ting

0.77

ters

0.74

Activations Density 0.027%

phrases related to physically impacting or reaching a target

occurrences of the word "hit" in various contexts

No Comments

No Known Activations