INDEX

Explanations

phrases related to specific locations, potentially named places or districts

oai_token-act-pair · gpt-3.5-turbo

specific titles or names associated with television shows and movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

source

-0.65

wake

-0.65

oslav

-0.64

hub

-0.60

 Photographer

-0.60

worthiness

-0.60

uga

-0.60

iferation

-0.60

rano

-0.59

giving

-0.59

POSITIVE LOGITS

undred

1.04

ĪĴ

0.87

ixty

0.78

 Wonders

0.70

 Eight

0.69

 Authentication

0.69

 Nine

0.68

 Scotch

0.67

imensional

0.67

ousand

0.67

Activations Density 0.139%

phrases related to specific locations, potentially named places or districts

specific titles or names associated with television shows and movies

No Comments

No Known Activations