INDEX

Explanations

pronouns referring to a specific male individual

oai_token-act-pair · gpt-3.5-turbo

references to a specific subject, indicating a focus on a singular male character throughout the text

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

 Peak

-0.69

 Killing

-0.67

reshold

-0.65

earch

-0.63

keleton

-0.60

peak

-0.59

Interest

-0.59

 Girls

-0.59

htaking

-0.59

Temperature

-0.58

POSITIVE LOGITS

'd

1.28

'll

1.20

 wrote

1.01

zbollah

0.95

eded

0.93

 tweeted

0.89

resy

0.87

 ported

0.86

've

0.85

pherd

0.84

Activations Density 0.254%

pronouns referring to a specific male individual

references to a specific subject, indicating a focus on a singular male character throughout the text

No Comments

No Known Activations