INDEX

Explanations

words related to combustion or intense energy release

oai_token-act-pair · gpt-3.5-turbo

words related to fire or ignition events

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

Not in Any Lists

No Comments

Negative Logits

romy

-0.84

alian

-0.81

alth

-0.80

iago

-0.79

oral

-0.75

roman

-0.73

umbo

-0.70

usterity

-0.70

ull

-0.68

ression

-0.67

POSITIVE LOGITS

 combust

1.26

 ignition

1.17

 ashes

1.14

ign

1.14

 ignite

1.13

 fuse

0.92

 ignited

0.90

 FIRE

0.90

 extingu

0.89

ash

0.89

Activations Density 0.017%

words related to combustion or intense energy release

words related to fire or ignition events

No Comments

No Known Activations