INDEX

Explanations

unexpected events or situations

oai_token-act-pair · gpt-3.5-turbo

the concept of unexpected occurrences or surprises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nan

-0.94

burgh

-0.91

tein

-0.87

ateurs

-0.83

imore

-0.83

rated

-0.81

builders

-0.79

ucc

-0.78

xia

-0.76

ogun

-0.75

POSITIVE LOGITS

 unexpected

0.86

cffffcc

0.84

LY

0.83

 surprises

0.78

 pregnancies

0.77

aneously

0.77

 twists

0.75

 Squid

0.74

 occurrences

0.74

ãĥĻ

0.72

Activations Density 0.034%

unexpected events or situations

the concept of unexpected occurrences or surprises

No Comments

No Known Activations