INDEX

Explanations

names containing the word "Prim" or derivations thereof

oai_token-act-pair · gpt-3.5-turbo

references to the term "Prim" or any variations related to it

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

lihood

-0.79

INESS

-0.79

IGH

-0.78

isSpecialOrderable

-0.70

UGE

-0.69

 Graveyard

-0.69

jriwal

-0.68

UGH

-0.68

IELD

-0.67

kson

-0.66

POSITIVE LOGITS

itives

1.47

itive

1.28

ordial

1.28

arily

1.08

rose

0.99

acy

0.94

ument

0.92

eness

0.90

atis

0.89

archs

0.87

Activations Density 0.020%

names containing the word "Prim" or derivations thereof

references to the term "Prim" or any variations related to it

No Comments

No Known Activations