INDEX

Explanations

verbs related to accusations, leveling, or charging

oai_token-act-pair · gpt-3.5-turbo

words related to accusations or claims made against entities

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

natureconservancy

-0.81

 Sidd

-0.77

enegger

-0.75

 Quantum

-0.71

 Leilan

-0.69

 Experimental

-0.68

 Constantin

-0.67

Opt

-0.67

icho

-0.63

umbn

-0.62

POSITIVE LOGITS

 leveled

1.34

 leve

1.29

lling

1.03

lled

0.92

 leveling

0.79

sheet

0.77

tones

0.75

itized

0.74

aton

0.72

sheets

0.72

Activations Density 0.028%

verbs related to accusations, leveling, or charging

words related to accusations or claims made against entities

No Comments

No Known Activations