INDEX

Explanations

names involving the word "Hans"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Hans" 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 @ 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

 Scotia

-0.87

aneously

-0.84

selves

-0.70

ctica

-0.69

bably

-0.68

ersion

-0.68

 IMAGES

-0.66

cial

-0.66

otions

-0.65

ments

-0.64

POSITIVE LOGITS

hin

1.05

 Andersen

0.94

sein

0.93

iewicz

0.85

hus

0.84

hu

0.83

furt

0.81

-+

0.79

kj

0.78

von

0.77

Activations Density 0.018%

names involving the word "Hans"

references to the name "Hans" and related variations

No Comments

No Known Activations