INDEX

Explanations

mentions of a specific name or term - "Ap" followed by a numeric value

oai_token-act-pair · gpt-3.5-turbo

references to "Apes" in various contexts, particularly in relation to movies and culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Lauder

-0.71

 Islanders

-0.69

 Jenner

-0.69

å§«

-0.69

hips

-0.67

åŃĲ

-0.67

 Continued

-0.66

 Hurricanes

-0.65

 Sands

-0.64

enegger

-0.64

POSITIVE LOGITS

artment

1.43

ocalyptic

1.33

ollo

1.29

ocalypse

1.18

ocaly

1.16

ologies

1.10

athetic

1.08

rax

1.06

athy

1.06

otrop

1.05

Activations Density 0.012%

mentions of a specific name or term - "Ap" followed by a numeric value

references to "Apes" in various contexts, particularly in relation to movies and culture

No Comments

No Known Activations