INDEX

Explanations

movie directors

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dir" and its variations, indicating a focus on film direction and related terminology

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

 Audit

-0.70

 Dragonbound

-0.67

ATES

-0.65

 Partnership

-0.62

ATURES

-0.62

ATURE

-0.62

 Alert

-0.62

 Button

-0.61

 Term

-0.61

arella

-0.61

POSITIVE LOGITS

ited

0.95

kish

0.95

kies

0.95

sonian

0.95

kers

0.94

ried

0.92

bing

0.91

kie

0.90

ned

0.89

ffer

0.88

Activations Density 0.073%

movie directors

instances of the word "dir" and its variations, indicating a focus on film direction and related terminology

No Comments

No Known Activations