INDEX

Explanations

terms related to a specific geographical location, Pennsylvania

oai_token-act-pair · gpt-3.5-turbo

mentions of the state of Pennsylvania

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

gers

-0.86

eer

-0.81

ging

-0.79

ged

-0.79

cam

-0.77

gement

-0.76

selage

-0.74

uers

-0.73

lasses

-0.73

Cub

-0.73

POSITIVE LOGITS

sylvania

1.47

 Railroad

1.04

 Avenue

0.99

 Berks

0.89

sylv

0.88

 State

0.88

ipher

0.85

 Borough

0.83

 Mellon

0.83

 Springs

0.81

Activations Density 0.013%

terms related to a specific geographical location, Pennsylvania

mentions of the state of Pennsylvania

No Comments

No Known Activations