INDEX

Explanations

special characters and non-English text

oai_token-act-pair · gpt-3.5-turbo

the special character 'Ħ' and related symbols or sequences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

geries

-0.94

 distracting

-0.84

 distracted

-0.74

 foreground

-0.71

 responders

-0.69

 Catalyst

-0.66

 offending

-0.66

 explan

-0.65

 regul

-0.65

 answ

-0.65

POSITIVE LOGITS

Ð¸

1.04

ski

0.92

à¸

0.91

æŃ¦

0.90

Ð¾

0.90

ĳ

0.89

Ð°

0.88

Ħ

0.87

APH

0.86

ï¸

0.86

Activations Density 0.007%

special characters and non-English text

the special character 'Ħ' and related symbols or sequences

No Comments

No Known Activations