INDEX

Explanations

the word "Marc"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Marc"

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

OTE

-0.78

itness

-0.75

velt

-0.75

FUL

-0.75

milo

-0.72

worldly

-0.68

irlf

-0.67

LLOW

-0.65

 SEAL

-0.65

SUP

-0.64

POSITIVE LOGITS

agne

0.94

ouf

0.94

afort

0.92

otti

0.90

ias

0.87

oses

0.86

anson

0.86

 Marc

0.86

ia

0.85

ques

0.84

Activations Density 0.010%

the word "Marc"

occurrences of the name "Marc"

No Comments

No Known Activations