INDEX

Explanations

terms related to individuals or groups who are involved in various activities or professions

oai_token-act-pair · gpt-3.5-turbo

words related to roles and positions within organizations or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 situational

-0.68

 Thing

-0.63

ASED

-0.62

 conviction

-0.61

 Ecology

-0.60

 bilateral

-0.58

OVER

-0.58

 Connection

-0.58

 increments

-0.58

OUT

-0.57

POSITIVE LOGITS

hip

1.55

hips

1.32

paces

1.26

ervatives

1.19

ettings

1.08

mith

1.06

pace

1.04

peak

0.98

heet

0.97

ervative

0.95

Activations Density 0.140%

terms related to individuals or groups who are involved in various activities or professions

words related to roles and positions within organizations or groups

No Comments

No Known Activations