INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and specific references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Ħ¢

-0.68

 Abbey

-0.68

âķĲâķĲ

-0.66

 Sevent

-0.64

::::::::

-0.64

"]=>

-0.63

raints

-0.62

selves

-0.61

 Allaah

-0.60

 Remastered

-0.59

POSITIVE LOGITS

esome

1.12

enhagen

1.04

 Klux

0.97

grim

0.87

ivil

0.85

Gru

0.84

etz

0.82

nder

0.82

bage

0.80

ulkan

0.79

Activations Density 0.012%

proper nouns

proper nouns, particularly names and specific references

No Comments

No Known Activations