INDEX

Explanations

proper nouns related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

specific sequences or abbreviations related to organizations or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

idious

-0.81

ternity

-0.80

ulence

-0.77

sheet

-0.75

enstein

-0.74

chwitz

-0.74

furt

-0.73

zig

-0.72

iator

-0.72

dyl

-0.70

POSITIVE LOGITS

 County

1.31

 Islands

1.22

 Heights

1.14

 Hills

1.04

 Tribe

1.03

 Coast

1.01

 Parish

1.00

 Highway

0.95

 Springs

0.95

 Highlands

0.94

Activations Density 0.162%

proper nouns related to geographical locations

specific sequences or abbreviations related to organizations or locations

No Comments

No Known Activations