INDEX

Explanations

unique and distinctive features or attributes

oai_token-act-pair · gpt-3.5-turbo

descriptive terms that emphasize uniqueness or particular traits

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

ergy

-0.78

©¶æ

-0.76

erg

-0.76

sent

-0.73

married

-0.72

jury

-0.72

ttp

-0.71

ceans

-0.71

source

-0.70

gres

-0.69

POSITIVE LOGITS

eatures

0.92

 distinctive

0.90

ively

0.90

 landmarks

0.88

 likeness

0.86

 traits

0.82

 distingu

0.79

 characteristics

0.78

isable

0.78

 characteristic

0.77

Activations Density 0.031%

unique and distinctive features or attributes

descriptive terms that emphasize uniqueness or particular traits

No Comments

No Known Activations