INDEX

Explanations

the word "whatever"

oai_token-act-pair · gpt-3.5-turbo

the word "whatever" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

enburg

-0.81

por

-0.80

enberg

-0.79

iv

-0.77

stra

-0.76

eds

-0.75

 Range

-0.72

lee

-0.71

ids

-0.71

et

-0.70

POSITIVE LOGITS

soever

1.23

wcsstore

1.03

 else

1.02

 whatever

0.90

whatever

0.90

 toget

0.88

 happ

0.83

 transpired

0.82

 floats

0.81

 happened

0.78

Activations Density 0.009%

the word "whatever"

the word "whatever" in various contexts

No Known Activations