INDEX

Explanations

terms related to volcanoes and volcanic activity

oai_token-act-pair · gpt-3.5-turbo

references to volcanic activity and features

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

abet

-0.78

ership

-0.75

anded

-0.73

winner

-0.73

lessly

-0.71

epad

-0.71

Score

-0.69

Lex

-0.69

agle

-0.69

arel

-0.68

POSITIVE LOGITS

eru

1.41

 eruption

1.23

 volcan

0.99

 volcanic

0.99

 lava

0.97

 erupt

0.96

 volcano

0.95

 erupted

0.94

cano

0.90

 crater

0.89

Activations Density 0.033%

terms related to volcanoes and volcanic activity

references to volcanic activity and features

No Comments

No Known Activations