INDEX

Explanations

words related to solutions or remedies for problems

oai_token-act-pair · gpt-3.5-turbo

terms related to solutions or fixes for problems

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

irl

-0.82

ker

-0.76

erness

-0.69

ammy

-0.66

oard

-0.66

ographic

-0.65

oak

-0.64

rome

-0.63

oths

-0.63

*/(

-0.63

POSITIVE LOGITS

 remedy

1.13

 remedies

0.99

 redress

0.82

ptoms

0.75

ãĤ©

0.69

 solutions

0.69

utics

0.68

atives

0.68

izon

0.68

 solves

0.68

Activations Density 0.006%

words related to solutions or remedies for problems

terms related to solutions or fixes for problems

No Comments

No Known Activations