INDEX

Explanations

proper names "Shane"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Shane."

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

é¾įå¥ĳå£«

-0.89

anooga

-0.87

ļé

-0.86

é¾įåĸļå£«

-0.83

rylic

-0.81

lished

-0.77

rium

-0.77

ents

-0.76

rontal

-0.76

ental

-0.74

POSITIVE LOGITS

lessly

0.96

 Shane

0.91

 Leone

0.82

 Bauer

0.76

 Spiegel

0.75

 Kier

0.72

 McMahon

0.72

forth

0.70

 Dempsey

0.68

 Moran

0.68

Activations Density 0.039%

proper names "Shane"

occurrences of the name "Shane."

No Comments

No Known Activations