INDEX

Explanations

proper nouns that refer to specific locations or entities

oai_token-act-pair · gpt-3.5-turbo

place names or geographical locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptoms

-0.81

vous

-0.77

ratulations

-0.73

andals

-0.72

enegger

-0.72

raints

-0.68

sylv

-0.66

berman

-0.65

doms

-0.64

ilies

-0.64

POSITIVE LOGITS

 behest

0.91

 intersections

0.87

Aren

0.84

 expense

0.83

 apiece

0.81

bury

0.74

 checkpoints

0.71

 Point

0.70

 checkpoint

0.70

 helm

0.68

Activations Density 0.286%

proper nouns that refer to specific locations or entities

place names or geographical locations

No Comments

No Known Activations