INDEX

Explanations

references to famous TV shows and games

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to television shows, companies, and notable figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ounter

-0.77

 charism

-0.69

ients

-0.68

opal

-0.64

urches

-0.64

ross

-0.63

otomy

-0.63

 narciss

-0.63

quo

-0.61

jriwal

-0.61

POSITIVE LOGITS

 Labs

0.80

lake

0.76

Sharp

0.72

DB

0.70

Score

0.69

 Genetics

0.69

Movie

0.68

Hack

0.68

Hub

0.67

pedia

0.67

Activations Density 0.233%

references to famous TV shows and games

proper nouns related to television shows, companies, and notable figures

No Comments

No Known Activations