INDEX

Explanations

phrases introducing new information or shifting focus

oai_token-act-pair · gpt-3.5-turbo

the word "here" 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 @ 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

ONSORED

-0.77

arij

-0.61

 externalToEVAOnly

-0.59

ORPG

-0.58

 actionGroup

-0.58

Edge

-0.58

ahime

-0.55

EStreamFrame

-0.55

è¦ļéĨĴ

-0.53

ãĥīãĥ©

-0.53

POSITIVE LOGITS

tical

1.05

 goes

1.00

tic

0.97

tics

0.97

 Comes

0.95

abouts

0.93

are

0.92

is

0.89

 comes

0.86

's

0.83

Activations Density 0.035%

phrases introducing new information or shifting focus

the word "here" in various contexts

No Comments

No Known Activations