INDEX

Explanations

phrases related to the absence or removal of something, often with negative connotations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "less."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BAT

-0.77

BIT

-0.72

MAG

-0.69

NEWS

-0.69

oÄŁ

-0.69

aeper

-0.68

ERN

-0.67

MA

-0.67

BU

-0.67

 Clause

-0.66

POSITIVE LOGITS

edly

0.89

 autom

0.76

hearted

0.71

 bystand

0.71

lihood

0.67

icity

0.67

uced

0.66

itary

0.66

enne

0.64

theless

0.63

Activations Density 0.026%

phrases related to the absence or removal of something, often with negative connotations

instances of the word "less."

No Comments

No Known Activations