INDEX

Explanations

references to places or individuals with the name "Lang"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Lang" and related variations

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

ItemTracker

-0.85

awaru

-0.76

 compensated

-0.75

 eleph

-0.75

Ĥª

-0.72

×ĳ

-0.71

ÏĢ

-0.71

irements

-0.70

hift

-0.69

ittee

-0.68

POSITIVE LOGITS

 Lang

1.08

strom

1.03

ford

1.02

enberg

0.99

ley

0.97

mu

0.90

dale

0.90

gow

0.89

ston

0.86

ued

0.84

Activations Density 0.016%

references to places or individuals with the name "Lang"

references to the name "Lang" and related variations

No Comments

No Known Activations