INDEX

Explanations

proper nouns related to sports or entertainment, such as names of athletes or actors

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or entities, particularly in the context of news or public affairs

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ãĥĥãĥī

-0.69

ERG

-0.66

ELS

-0.65

Market

-0.62

resh

-0.62

Morning

-0.61

iPhone

-0.60

ajor

-0.60

TPS

-0.60

rew

-0.59

POSITIVE LOGITS

getic

0.85

ogly

0.84

hoe

0.79

cing

0.79

cest

0.77

ced

0.77

xes

0.75

stadt

0.73

cer

0.73

dain

0.73

Activations Density 0.058%

proper nouns related to sports or entertainment, such as names of athletes or actors

references to specific individuals or entities, particularly in the context of news or public affairs

No Known Activations