INDEX

Explanations

instances of the word "seen" in sentences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "seen."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

vernment

-0.73

orrect

-0.67

 unification

-0.67

 anthem

-0.65

eware

-0.64

ses

-0.63

 misunderstanding

-0.63

angan

-0.62

 integration

-0.62

 perm

-0.61

POSITIVE LOGITS

IOR

0.92

IRT

0.90

../

0.87

Ĺ

0.85

seeing

0.85

wcsstore

0.85

PsyNetMessage

0.83

 Seen

0.78

ById

0.78

ĸļ

0.78

Activations Density 0.028%

instances of the word "seen" in sentences

occurrences of the word "seen."

No Comments

No Known Activations