INDEX

Explanations

instances of the word "base" followed by a number representing a level of importance or significance

oai_token-act-pair · gpt-3.5-turbo

references to foundational aspects or elements within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

apes

-0.72

icut

-0.71

odd

-0.70

ulp

-0.68

NESS

-0.67

 Daly

-0.67

icer

-0.66

ipping

-0.65

osen

-0.65

 Rollins

-0.64

POSITIVE LOGITS

camp

1.04

plate

0.86

plates

0.82

base

0.78

plan

0.78

 base

0.76

ball

0.74

 structure

0.73

rame

0.72

mate

0.71

Activations Density 0.016%

instances of the word "base" followed by a number representing a level of importance or significance

references to foundational aspects or elements within a context

No Comments

No Known Activations