INDEX

Explanations

keywords related to storms or storm-related terms

oai_token-act-pair · gpt-3.5-turbo

references to "Storm" or related characters/themes

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

entary

-0.95

ĸļ

-0.90

ADRA

-0.85

terior

-0.84

ablished

-0.81

ASED

-0.80

untu

-0.80

ately

-0.79

ablishment

-0.78

duction

-0.78

POSITIVE LOGITS

tro

1.32

 troopers

0.99

 Trooper

0.97

bringer

0.96

 Storm

0.91

claw

0.89

 trooper

0.85

water

0.84

light

0.83

front

0.82

Activations Density 0.012%

keywords related to storms or storm-related terms

references to "Storm" or related characters/themes

No Comments

No Known Activations