INDEX

Explanations

names of people and places

oai_token-act-pair · gpt-3.5-turbo

names or proper nouns related to people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SPONSORED

-0.75

$$$$

-0.65

 respectively

-0.64

 pent

-0.62

 helm

-0.61

 guid

-0.58

 maximizing

-0.57

shapeshifter

-0.57

 gradient

-0.57

EVs

-0.57

POSITIVE LOGITS

utsu

0.84

oni

0.79

udos

0.77

omon

0.75

onia

0.75

inder

0.73

unda

0.73

 Profile

0.72

aun

0.72

orm

0.72

Activations Density 0.359%

names of people and places

names or proper nouns related to people and organizations

No Comments

No Known Activations