INDEX

Explanations

numerical expressions related to quantities or values

oai_token-act-pair · gpt-3.5-turbo

numerical data or identifiers related to quantities and measurements

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

ches

-0.74

ched

-0.72

abol

-0.71

alyses

-0.70

tern

-0.69

hunt

-0.69

colm

-0.65

abolic

-0.63

agara

-0.63

forces

-0.62

POSITIVE LOGITS

0.86

iations

0.71

 ILCS

0.70

rpm

0.68

racted

0.68

iated

0.68

 litres

0.66

MHz

0.66

sie

0.66

rous

0.65

Activations Density 0.054%

numerical expressions related to quantities or values

numerical data or identifiers related to quantities and measurements

No Comments

No Known Activations