INDEX

Explanations

names of locations or organizations

oai_token-act-pair · gpt-3.5-turbo

common nouns or proper nouns associated with names or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

glers

-0.59

perty

-0.58

 utmost

-0.57

drivers

-0.57

steamapps

-0.56

 tooth

-0.55

 mutants

-0.54

stroke

-0.53

 highs

-0.53

 takeoff

-0.53

POSITIVE LOGITS

usa

0.76

oola

0.76

qua

0.69

èĢħ

0.68

nikov

0.67

 Pradesh

0.67

DragonMagazine

0.65

yne

0.64

IRC

0.64

à¼

0.64

Activations Density 0.269%

names of locations or organizations

common nouns or proper nouns associated with names or entities

No Comments

No Known Activations