INDEX

Explanations

specific mentions of ranches

oai_token-act-pair · gpt-3.5-turbo

mentions of ranches

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

lihood

-0.68

 dism

-0.65

ABLE

-0.63

*/(

-0.61

Bok

-0.60

 chromos

-0.59

 Wong

-0.58

 Bucc

-0.57

 decom

-0.56

 Commonwealth

-0.56

POSITIVE LOGITS

 ranch

0.96

ing

0.83

ington

0.82

 Bundy

0.81

yard

0.81

agna

0.80

aires

0.77

 Ranch

0.76

oise

0.75

naire

0.74

Activations Density 0.017%

specific mentions of ranches

mentions of ranches

No Comments

No Known Activations