INDEX

Explanations

references to military raids or attacks

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "raid"

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

 Scotia

-0.77

Bie

-0.75

 Regina

-0.71

 Mellon

-0.69

 Genie

-0.68

DonaldTrump

-0.68

 Rosenstein

-0.67

 Holden

-0.66

éĸ

-0.65

Seb

-0.65

POSITIVE LOGITS

ers

0.89

raid

0.88

 raid

0.83

*=-

0.82

Raid

0.79

doms

0.79

iness

0.78

ishly

0.78

iversary

0.73

 raiding

0.73

Activations Density 0.021%

references to military raids or attacks

occurrences of the word "raid"

No Comments

No Known Activations