INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

names of people and notable figures

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

 targ

-0.81

 Munich

-0.77

redit

-0.73

 Dian

-0.67

meg

-0.66

 phys

-0.65

 synd

-0.65

 hots

-0.65

Ds

-0.64

PK

-0.64

POSITIVE LOGITS

Vas

1.85

 Emily

1.71

Emily

1.49

 Coffin

1.07

 Vance

1.04

 Coff

1.00

 Rochester

0.98

 Gupta

0.94

 Caleb

0.94

 Claire

0.93

Activations Density 0.043%

names of people

names of people and notable figures

No Comments

No Known Activations