INDEX

Explanations

phrases containing variations of the word "drop" and "Drozov"

oai_token-act-pair · gpt-3.5-turbo

the word "dro" 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Corp

-0.73

 Woodward

-0.71

 Amos

-0.68

ATIONAL

-0.67

 Pagan

-0.67

Angelo

-0.67

UTC

-0.67

aya

-0.66

Nat

-0.65

English

-0.65

POSITIVE LOGITS

dro

4.16

dro

1.92

Dro

1.89

 droid

1.66

Dro

1.59

 Droid

1.34

 aeros

1.09

dri

1.07

gri

1.03

vap

1.01

Activations Density 0.020%

phrases containing variations of the word "drop" and "Drozov"

the word "dro" in various contexts

No Comments

No Known Activations