INDEX

Explanations

phrases related to the composition and characteristics of planetary atmospheres

oai_token-act-pair · gpt-3.5-turbo

references to "atmosphere."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

present

-0.76

skill

-0.74

UFC

-0.72

practice

-0.70

Pitt

-0.70

Franc

-0.68

Americans

-0.66

POS

-0.66

udeb

-0.66

Pont

-0.66

POSITIVE LOGITS

osphere

0.99

 ozone

0.97

heric

0.92

heres

0.84

mble

0.84

 atmosp

0.83

 atmosphere

0.82

 helium

0.80

 emitting

0.80

 haze

0.79

Activations Density 0.024%

phrases related to the composition and characteristics of planetary atmospheres

references to "atmosphere."

No Comments

No Known Activations