INDEX

Explanations

phrases related to making official statements

oai_token-act-pair · gpt-3.5-turbo

statements made by individuals in formal contexts

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

 penetration

-0.70

cius

-0.69

liest

-0.69

wat

-0.63

 impro

-0.63

 mismatch

-0.63

worm

-0.63

atron

-0.62

 Penet

-0.61

 eyed

-0.61

POSITIVE LOGITS

Statement

1.05

 "âĢ¦

0.82

 "...

0.81

 THANK

0.77

 apology

0.77

"#

0.76

:"

0.76

"@

0.74

 apologizing

0.74

 statement

0.74

Activations Density 0.339%

phrases related to making official statements

statements made by individuals in formal contexts

No Comments

No Known Activations