INDEX

Explanations

mentions of garbage or related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to waste management and refuse

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

hip

-0.90

saf

-0.83

nen

-0.83

lis

-0.78

ffield

-0.77

ning

-0.75

akening

-0.75

imble

-0.73

farious

-0.72

itude

-0.71

POSITIVE LOGITS

 dumps

1.00

 disposal

0.95

 garbage

0.90

 bags

0.86

 inciner

0.82

 collection

0.81

 cans

0.81

 dump

0.80

bags

0.80

 collector

0.78

Activations Density 0.017%

mentions of garbage or related terms

terms related to waste management and refuse

No Comments

No Known Activations