INDEX

Explanations

the word "Denny" with different activation strengths, specifically with an emphasis on the higher activations

oai_token-act-pair · gpt-3.5-turbo

the name "Lenny" in various contexts

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

pmwiki

-0.77

 behav

-0.74

itud

-0.72

-0.71

istical

-0.70

ioch

-0.70

juven

-0.70

ifier

-0.68

spring

-0.68

 Hurricanes

-0.65

POSITIVE LOGITS

oshenko

0.88

enny

0.75

hyde

0.75

utical

0.73

ollar

0.73

 Arcade

0.72

roach

0.67

ption

0.67

bles

0.67

wallet

0.67

Activations Density 0.009%

the word "Denny" with different activation strengths, specifically with an emphasis on the higher activations

the name "Lenny" in various contexts

No Comments

No Known Activations