INDEX

Explanations

terms related to legal and bureaucratic entities and procedures

oai_token-act-pair · gpt-3.5-turbo

terms related to law enforcement and public health

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acca

-0.80

 Kinnikuman

-0.75

 Hispan

-0.68

idious

-0.66

íķ

-0.63

ighty

-0.63

heny

-0.63

EStream

-0.61

rupulous

-0.61

dinand

-0.60

POSITIVE LOGITS

mbudsman

0.73

 macro

0.68

 codes

0.67

eworks

0.66

 credential

0.65

classes

0.65

store

0.64

lance

0.63

 prize

0.63

odox

0.62

Activations Density 0.468%

terms related to legal and bureaucratic entities and procedures

terms related to law enforcement and public health

No Comments

No Known Activations