INDEX

Explanations

locations or places described as "central" within the context it reads

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "central" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TED

-0.82

Maker

-0.81

rieve

-0.78

FREE

-0.77

Brave

-0.74

%%

-0.73

isSpecialOrderable

-0.73

UE

-0.72

tm

-0.72

uge

-0.72

POSITIVE LOGITS

ised

1.07

 arteries

0.98

 artery

0.95

ization

0.90

 nervous

0.90

izing

0.90

isation

0.88

ized

0.83

ising

0.79

izes

0.79

Activations Density 0.016%

locations or places described as "central" within the context it reads

occurrences of the word "central" in various contexts

No Comments

No Known Activations