INDEX

Explanations

names and terms related to a specific person or organization ending in "hart."

oai_token-act-pair · gpt-3.5-turbo

names or terms that include the substring 'hart.'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

URI

-0.77

 millenn

-0.69

 veter

-0.68

 sclerosis

-0.67

 medic

-0.66

ntil

-0.65

Loading

-0.65

 Palestin

-0.64

 breaches

-0.63

ISSION

-0.62

POSITIVE LOGITS

hart

1.13

enstein

1.02

ford

0.98

ilton

0.88

zman

0.86

ness

0.84

ãĤ¤ãĥĪ

0.83

hardt

0.83

mann

0.81

otle

0.81

Activations Density 0.008%

names and terms related to a specific person or organization ending in "hart."

names or terms that include the substring 'hart.'

No Comments

No Known Activations