INDEX

Explanations

pronouns (he, she, they) followed by verbs indicating speech or action

oai_token-act-pair · gpt-3.5-turbo

statements or claims made by individuals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acters

-0.69

eating

-0.66

wcsstore

-0.64

rocket

-0.63

ancial

-0.63

rame

-0.62

usha

-0.61

uitous

-0.60

 Benefit

-0.60

alian

-0.59

POSITIVE LOGITS

 argued

0.82

'd

0.82

 reasoned

0.81

 said

0.80

 says

0.78

say

0.78

 argues

0.76

©¶æ¥µ

0.75

 argue

0.73

 pointed

0.67

Activations Density 0.237%

pronouns (he, she, they) followed by verbs indicating speech or action

statements or claims made by individuals

No Comments

No Known Activations