INDEX

Explanations

concepts related to theories and cognitive processes

oai_token-act-pair · gpt-3.5-turbo

concepts and terms related to learning theory and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

udeb

-0.74

Ire

-0.68

 nightly

-0.66

GMT

-0.65

 Slim

-0.64

 Commodore

-0.64

 Leopard

-0.63

UAE

-0.62

tips

-0.62

 Dell

-0.61

POSITIVE LOGITS

 theory

1.22

 Theory

1.22

 causation

1.09

 theorists

1.08

 epist

1.07

ivism

1.07

ilitarian

1.05

 versus

1.04

vs

1.01

 hypothesis

1.01

Activations Density 0.636%

concepts related to theories and cognitive processes

concepts and terms related to learning theory and its implications

No Comments

No Known Activations