INDEX

Explanations

phrases related to descriptions, explanations, or observations

oai_token-act-pair · gpt-3.5-turbo

statements and assertions about current conditions or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

eor

-0.72

agues

-0.69

ievers

-0.69

iard

-0.64

 ceremon

-0.64

aints

-0.62

 whis

-0.61

 helm

-0.60

luaj

-0.59

aine

-0.58

POSITIVE LOGITS

olation

0.78

 Madness

0.76

 extraordinary

0.75

 nothing

0.75

 astounding

0.73

olated

0.72

 something

0.71

Reviewer

0.71

KER

0.70

 unbelievable

0.70

Activations Density 0.121%

phrases related to descriptions, explanations, or observations

statements and assertions about current conditions or observations

No Comments

No Known Activations