INDEX

Explanations

numbers and measurements

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring 'VER' or related word patterns

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

essler

-0.59

Downloadha

-0.55

Õ

-0.54

staking

-0.54

iewicz

-0.53

 Chop

-0.53

 cush

-0.53

 manure

-0.51

:,

-0.50

Zup

-0.50

POSITIVE LOGITS

ese

0.61

FORE

0.56

enment

0.56

antle

0.55

 Revival

0.53

 Advent

0.51

ebus

0.51

iasm

0.51

ribune

0.51

Pacific

0.51

Activations Density 0.232%

numbers and measurements

occurrences of the substring 'VER' or related word patterns

No Comments

No Known Activations