INDEX

Explanations

instances of words related to making changes

oai_token-act-pair · gpt-3.5-turbo

references to changes or modifications 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

horn

-0.71

 Cosponsors

-0.70

Got

-0.62

vo

-0.60

EMOTE

-0.58

 boycot

-0.58

Bu

-0.57

CI

-0.56

ace

-0.56

 PLUS

-0.56

POSITIVE LOGITS

 clarify

0.93

dos

0.88

 appease

0.87

 ensure

0.85

 postpone

0.81

 minimize

0.80

 improve

0.79

 accommodate

0.79

 eliminate

0.77

 occur

0.76

Activations Density 0.094%

instances of words related to making changes

references to changes or modifications in various contexts

No Comments

No Known Activations