INDEX

Explanations

tokens indicating a new sentence or the start of a new text segment

oai_token-act-pair · gpt-3.5-turbo

the indefinite article "a" 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 @ 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

assisted

-0.89

breakers

-0.77

anism

-0.75

enance

-0.74

OWS

-0.74

eyes

-0.73

tags

-0.72

friends

-0.71

rates

-0.70

ares

-0.69

POSITIVE LOGITS

lot

1.31

 possibility

1.21

 shortage

1.21

 tendency

1.19

 plethora

1.18

 definite

1.06

 discrepancy

1.02

 tremendous

1.02

LOT

1.01

 chance

1.01

Activations Density 0.093%

tokens indicating a new sentence or the start of a new text segment

the indefinite article "a" in various contexts

No Comments

No Known Activations