INDEX

Explanations

keywords related to meaningful actions or events

oai_token-act-pair · gpt-3.5-turbo

the word "meaningful" and its variations

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

Not in Any Lists

No Comments

Negative Logits

cephal

-0.71

 Tycoon

-0.70

cler

-0.70

nery

-0.69

roid

-0.68

rix

-0.68

resp

-0.67

cker

-0.66

peak

-0.65

ois

-0.65

POSITIVE LOGITS

issance

0.88

 meaningful

0.86

 newcom

0.82

terday

0.82

itized

0.81

 guiActiveUn

0.79

 lapt

0.77

 ende

0.77

 shorth

0.76

ively

0.75

Activations Density 0.011%

keywords related to meaningful actions or events

the word "meaningful" and its variations

No Comments

No Known Activations