INDEX

Explanations

phrases related to transportation incidents or accidents

oai_token-act-pair · gpt-3.5-turbo

references to vehicle accidents or crashes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

arov

-0.74

icrobial

-0.65

byter

-0.65

egal

-0.64

achu

-0.63

THER

-0.62

Ĭ±

-0.62

ophers

-0.62

tains

-0.62

TERN

-0.61

POSITIVE LOGITS

 crashes

1.08

 crash

1.08

Crash

1.04

 Crash

1.01

 Dive

0.92

 crashed

0.87

worthiness

0.86

 wreck

0.79

 crater

0.79

dump

0.75

Activations Density 0.011%

phrases related to transportation incidents or accidents

references to vehicle accidents or crashes

No Comments

No Known Activations