INDEX

Explanations

phrases expressing a cause-and-effect relationship, particularly emphasizing a resulting consequence

oai_token-act-pair · gpt-3.5-turbo

the word "so" used to indicate a consequential or emphatic statement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

enaries

-0.61

eneg

-0.59

agon

-0.59

idon

-0.59

intosh

-0.57

efe

-0.56

atars

-0.55

umbn

-0.55

dust

-0.55

enary

-0.53

POSITIVE LOGITS

oner

1.16

bered

1.06

oths

1.05

apy

0.93

vere

0.91

othes

0.89

othe

0.88

far

0.88

 long

0.87

othing

0.87

Activations Density 0.059%

phrases expressing a cause-and-effect relationship, particularly emphasizing a resulting consequence

the word "so" used to indicate a consequential or emphatic statement

No Comments

No Known Activations