INDEX

Explanations

causal relationships or explanations in the text

oai_token-act-pair · gpt-3.5-turbo

terms related to causation and causal relationships

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

 Leopard

-0.82

ardless

-0.68

HCR

-0.66

 Unicorn

-0.66

Gro

-0.65

>>>>>>>>

-0.65

 Flake

-0.65

Pip

-0.63

ushes

-0.63

chip

-0.62

POSITIVE LOGITS

ality

1.13

 caus

0.96

istically

0.91

ally

0.89

ities

0.86

atorial

0.85

allo

0.84

uristic

0.79

 inference

0.77

ually

0.76

Activations Density 0.018%

causal relationships or explanations in the text

terms related to causation and causal relationships

No Comments

No Known Activations