INDEX

Explanations

words related to conflict or battle

oai_token-act-pair · gpt-3.5-turbo

references to fighting or struggle in various contexts

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

ographical

-0.71

essage

-0.70

acher

-0.68

 Seym

-0.67

Ħ¢

-0.66

uras

-0.66

 Shutdown

-0.66

ardy

-0.66

DragonMagazine

-0.65

Newsletter

-0.65

POSITIVE LOGITS

 against

1.05

 valiant

0.88

fighting

0.81

fight

0.79

 passionately

0.79

 waged

0.78

 alongside

0.78

 fiercely

0.77

 fought

0.77

fights

0.76

Activations Density 0.036%

words related to conflict or battle

references to fighting or struggle in various contexts

No Comments

No Known Activations