INDEX

Explanations

mentions of famous people, places, and events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "famous" used to describe various subjects

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

THER

-0.76

ilation

-0.74

heed

-0.73

©¶æ

-0.71

otent

-0.69

owder

-0.69

plet

-0.67

adies

-0.66

idation

-0.66

opt

-0.66

POSITIVE LOGITS

rities

0.89

 landmarks

0.84

 BaseType

0.74

 quotes

0.73

 names

0.73

 recre

0.73

NESS

0.72

 comeback

0.69

 Circus

0.69

ness

0.68

Activations Density 0.023%

mentions of famous people, places, and events

instances of the word "famous" used to describe various subjects

No Comments

No Known Activations