INDEX

Explanations

mentions of long-term presence or activity in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing presence or activity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 secondly

-0.71

é¾į

-0.70

]]

-0.67

"},{"

-0.64

\-

-0.61

 Secondly

-0.60

 Primordial

-0.59

.;

-0.58

LIB

-0.58

Percent

-0.57

POSITIVE LOGITS

 limbo

0.82

 continuous

0.79

 intermitt

0.76

 continual

0.76

 since

0.76

 steady

0.75

 constant

0.74

since

0.74

 continuously

0.72

 steadily

0.71

Activations Density 0.098%

mentions of long-term presence or activity in various contexts

phrases indicating ongoing presence or activity in various contexts

No Comments

No Known Activations