INDEX

Explanations

terms related to combat or military operations

oai_token-act-pair · gpt-3.5-turbo

terms related to military combat and operations

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

gow

-0.76

Else

-0.71

eus

-0.70

ocument

-0.68

eton

-0.68

ocl

-0.66

ħĭ

-0.65

bye

-0.65

atron

-0.62

Choice

-0.60

POSITIVE LOGITS

iveness

0.94

fighting

0.88

ting

0.86

ant

0.82

ments

0.80

ants

0.80

 fatig

0.79

fighters

0.78

fighter

0.74

 prowess

0.73

Activations Density 0.025%

terms related to combat or military operations

terms related to military combat and operations

No Comments

No Known Activations