INDEX

Explanations

phrases related to specific names or titles of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Canaver

-0.67

 Angelo

-0.64

selves

-0.64

 Constantine

-0.63

 PROGRAM

-0.61

 defin

-0.60

 VIDEOS

-0.59

 Egyptians

-0.58

 Skydragon

-0.58

sep

-0.57

POSITIVE LOGITS

hai

0.85

atu

0.80

igham

0.77

Ô

0.77

liga

0.74

urst

0.73

istan

0.72

esi

0.72

jee

0.71

edu

0.69

Activations Density 0.268%

phrases related to specific names or titles of individuals

proper nouns and names of individuals

No Comments

No Known Activations