INDEX

Explanations

mentions of a specific person named "Denny" with varying levels of importance

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Denny" or variations of "penny."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 behav

-0.80

ivia

-0.70

 surv

-0.68

iour

-0.68

istical

-0.67

spring

-0.66

istically

-0.65

 dispel

-0.65

ãĤ±

-0.65

 challeng

-0.65

POSITIVE LOGITS

oshenko

0.80

acht

0.80

ollar

0.79

hyde

0.78

acci

0.76

bles

0.72

pend

0.72

wallet

0.72

enny

0.70

TERN

0.69

Activations Density 0.012%

mentions of a specific person named "Denny" with varying levels of importance

mentions of the name "Denny" or variations of "penny."

No Comments

No Known Activations