INDEX

Explanations

words related to challenges and obstacles

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

liv

-0.70

cffff

-0.66

psc

-0.64

dule

-0.62

elin

-0.61

srf

-0.60

ADRA

-0.57

ceans

-0.56

azard

-0.56

inav

-0.56

POSITIVE LOGITS

 involves

0.86

 relates

0.83

 imaginable

0.76

 revolves

0.76

is

0.75

 concerns

0.73

 derives

0.72

 lies

0.70

 arises

0.69

 resides

0.68

Activations Density 0.214%

words related to challenges and obstacles

No Comments

No Known Activations