INDEX

Explanations

phrases related to providing answers or solving problems

oai_token-act-pair · gpt-3.5-turbo

references to solutions or proposed solutions to problems

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

rob

-0.77

rica

-0.68

 livest

-0.68

prints

-0.68

ross

-0.67

NF

-0.65

head

-0.65

ammy

-0.64

rolled

-0.63

ardy

-0.63

POSITIVE LOGITS

Solution

0.84

 solutions

0.82

 thereto

0.80

 solve

0.77

olution

0.76

 solution

0.74

olutions

0.72

idian

0.71

 solving

0.71

vable

0.70

Activations Density 0.023%

phrases related to providing answers or solving problems

references to solutions or proposed solutions to problems

No Comments

No Known Activations