INDEX

Explanations

mention of conflicts or battles

oai_token-act-pair · gpt-3.5-turbo

the term "wars" and its variations in context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gow

-0.76

YL

-0.66

Dialogue

-0.66

opathy

-0.65

obook

-0.62

OGR

-0.61

uration

-0.61

STER

-0.61

urated

-0.61

 Accuracy

-0.60

POSITIVE LOGITS

hip

1.26

hips

1.14

 waged

0.95

 raged

0.83

 wars

0.83

pread

0.83

 raging

0.83

pite

0.82

pace

0.82

 fought

0.79

Activations Density 0.044%

mention of conflicts or battles

the term "wars" and its variations in context

No Comments

No Known Activations