INDEX

Explanations

mentions of individuals holding the title of "fellow" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to individuals with the title "fellow."

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

ARA

-0.73

DEN

-0.69

 DRAG

-0.66

 Retrieved

-0.66

 Archives

-0.64

 Tycoon

-0.63

 Sorceress

-0.62

 Ukrain

-0.62

ADE

-0.61

onies

-0.60

POSITIVE LOGITS

luaj

0.84

worldly

0.82

member

0.81

 classmates

0.78

ference

0.77

brook

0.76

 strugg

0.76

 travellers

0.76

workers

0.75

 traveler

0.74

Activations Density 0.008%

mentions of individuals holding the title of "fellow" in various contexts

references to individuals with the title "fellow."

No Comments

No Known Activations