INDEX

Explanations

words related to specific names of individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Hannon" and variations related to narrative or reporting

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

uries

-0.94

 livest

-0.76

 corrid

-0.75

mates

-0.74

urious

-0.73

linked

-0.69

locked

-0.67

ury

-0.66

alus

-0.65

 mathemat

-0.64

POSITIVE LOGITS

xual

0.96

GGGG

0.77

 Verge

0.75

 Depot

0.73

agement

0.71

 Examiner

0.71

UNCH

0.71

sbm

0.71

Gry

0.70

tsky

0.69

Activations Density 0.057%

words related to specific names of individuals

occurrences of the name "Hannon" and variations related to narrative or reporting

No Comments

No Known Activations