INDEX

Explanations

instances where an action is done or a state is described without a particular element or item

oai_token-act-pair · gpt-3.5-turbo

the phrase "without" and its repeated usage 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

oola

-0.87

mun

-0.87

raq

-0.82

omsky

-0.76

ulty

-0.74

mers

-0.72

des

-0.69

ocations

-0.69

cow

-0.69

ahime

-0.69

POSITIVE LOGITS

lessly

0.84

 knowing

0.82

 blinking

0.76

 sacrificing

0.70

 mentioning

0.70

 compromising

0.69

 interruption

0.69

 regard

0.69

 substit

0.69

 exception

0.66

Activations Density 0.038%

instances where an action is done or a state is described without a particular element or item

the phrase "without" and its repeated usage in different contexts

No Known Activations