INDEX

Explanations

proper names, specifically the name "Jake."

oai_token-act-pair · gpt-3.5-turbo

the name "Jake" in the context of various narratives or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 subst

-0.78

 semic

-0.78

VA

-0.72

olog

-0.69

 installations

-0.68

Lux

-0.67

 consec

-0.67

dec

-0.66

olic

-0.66

 cosmetics

-0.65

POSITIVE LOGITS

 Jake

3.44

Jake

3.14

 Alec

1.38

 Jared

1.36

 Joey

1.33

 Rory

1.33

 Shane

1.28

 Maggie

1.27

 Jace

1.24

 Ethan

1.24

Activations Density 0.015%

proper names, specifically the name "Jake."

the name "Jake" in the context of various narratives or descriptions

No Comments

No Known Activations