INDEX

Explanations

notable features or elements within different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "notable"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

claimer

-0.90

©¶æ

-0.85

tein

-0.81

ramid

-0.78

prep

-0.75

nan

-0.73

uv

-0.72

imeter

-0.72

oping

-0.71

romy

-0.70

POSITIVE LOGITS

Notable

0.90

 notable

0.90

 noteworthy

0.86

 landmarks

0.86

rities

0.84

NESS

0.84

 exceptions

0.83

 accomplishments

0.82

 milestones

0.81

 exception

0.81

Activations Density 0.011%

notable features or elements within different contexts

instances of the word "notable"

No Comments

No Known Activations