INDEX

Explanations

terms related to verticality or height

oai_token-act-pair · gpt-3.5-turbo

terms related to verticality and orientation in various contexts

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

enegger

-0.81

giving

-0.81

email

-0.77

cards

-0.76

REDACTED

-0.76

otle

-0.76

rug

-0.75

lyak

-0.75

ãģ®éŃĶ

-0.75

rament

-0.75

POSITIVE LOGITS

 axis

1.07

 stabil

0.96

 stripes

0.95

 displacement

0.91

 separation

0.91

 takeoff

0.90

 spacing

0.90

 scrolling

0.87

 dimension

0.86

 positioning

0.86

Activations Density 0.043%

terms related to verticality or height

terms related to verticality and orientation in various contexts

No Comments

No Known Activations