INDEX

Explanations

positive or favorable descriptors

oai_token-act-pair · gpt-3.5-turbo

instances of the word "good" signaling positive assessments or judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lees

-0.76

eds

-0.75

gemony

-0.71

isms

-0.69

anwhile

-0.69

redients

-0.68

dom

-0.68

 Syndrome

-0.67

chers

-0.67

eters

-0.66

POSITIVE LOGITS

 chunk

1.11

enough

1.03

 approximation

1.03

 deal

1.00

 example

0.95

 thing

0.93

 idea

0.93

 Samar

0.93

ol

0.92

sword

0.92

Activations Density 0.085%

positive or favorable descriptors

instances of the word "good" signaling positive assessments or judgments

No Comments

No Known Activations