INDEX

Explanations

words related to specific situations or locations

oai_token-act-pair · gpt-3.5-turbo

key nouns that indicate central themes or contexts in the document

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 desks

-0.68

 asteroids

-0.65

 parties

-0.61

 ceilings

-0.61

 Roof

-0.60

CLR

-0.60

 Doors

-0.60

asters

-0.59

 Sections

-0.59

tails

-0.59

POSITIVE LOGITS

cture

0.84

piece

0.73

iece

0.70

undrum

0.68

stros

0.67

oster

0.67

 cycle

0.66

cule

0.66

 sorely

0.66

claimer

0.65

Activations Density 0.241%

words related to specific situations or locations

key nouns that indicate central themes or contexts in the document

No Comments

No Known Activations