INDEX

Explanations

numerical values or patterns mixed with special characters and letters

oai_token-act-pair · gpt-3.5-turbo

special characters or non-standard symbols in the text

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

enegger

-0.78

inement

-0.72

 bombshell

-0.71

 advis

-0.71

agents

-0.68

 compr

-0.68

raints

-0.66

umers

-0.66

 relevance

-0.65

isance

-0.65

POSITIVE LOGITS

ħ

1.14

ĩ

0.98

Ð¾Ð

0.93

Į

0.92

Ĩ

0.89

İ

0.88

âĸĦ

0.84

ª

0.83

Ī

0.81

Ħ

0.79

Activations Density 0.007%

numerical values or patterns mixed with special characters and letters

special characters or non-standard symbols in the text

No Comments

No Known Activations