INDEX

Explanations

names or terms related to people or places

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'i' and its variations in different contexts

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

DERR

-0.72

 ende

-0.71

OTAL

-0.69

 Instr

-0.66

GGGGGGGG

-0.63

BILITIES

-0.62

thora

-0.60

vertisement

-0.60

APS

-0.59

JUST

-0.59

POSITIVE LOGITS

 hybrids

0.96

 hybrid

0.91

 alike

0.81

 combo

0.78

ioned

0.72

awed

0.67

 complexes

0.65

iton

0.64

iated

0.64

kered

0.64

Activations Density 0.303%

names or terms related to people or places

instances of the letter 'i' and its variations in different contexts

No Comments

No Known Activations