INDEX

Explanations

comparative terms indicating a higher level or degree of something

oai_token-act-pair · gpt-3.5-turbo

comparisons and superlative expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nikov

-0.75

 Zeal

-0.62

é¾įå

-0.61

Doctor

-0.60

contact

-0.59

CPU

-0.59

————

-0.58

egu

-0.58

tnc

-0.57

meg

-0.57

POSITIVE LOGITS

hest

0.79

osphere

0.74

 portion

0.71

iest

0.68

 longest

0.65

 tendency

0.65

icent

0.65

 part

0.65

mond

0.64

ħĭ

0.64

Activations Density 0.062%

comparative terms indicating a higher level or degree of something

comparisons and superlative expressions

No Comments

No Known Activations