INDEX

Explanations

the acronym "AA" across various contexts

oai_token-act-pair · gpt-3.5-turbo

classifications of credit ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

eering

-0.84

gro

-0.79

 Grizzlies

-0.75

bourg

-0.75

theless

-0.74

ĸļ

-0.74

ledge

-0.74

ified

-0.73

fully

-0.73

 Jenner

-0.71

POSITIVE LOGITS

QB

0.98

ECA

0.90

HAHA

0.80

ccess

0.78

VA

0.77

AM

0.77

HHHH

0.76

HAHAHAHA

0.75

ourt

0.74

qua

0.73

Activations Density 0.036%

the acronym "AA" across various contexts

classifications of credit ratings

No Comments

No Known Activations