INDEX

Explanations

mentions of armed conflict or battles

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fighting" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ħĭ

-0.80

æĺ¯

-0.74

uras

-0.72

ographical

-0.70

ophile

-0.69

ocl

-0.69

OGR

-0.68

Reviewer

-0.67

gow

-0.66

 Starship

-0.66

POSITIVE LOGITS

fighting

1.21

 raged

1.00

fights

0.97

 waged

0.97

fighters

0.96

 fatig

0.93

 against

0.92

 brig

0.87

 alongside

0.85

forces

0.84

Activations Density 0.052%

mentions of armed conflict or battles

instances of the word "fighting" and related terms

No Comments

No Known Activations