INDEX

Explanations

action words related to improvement or enhancement

oai_token-act-pair · gpt-3.5-turbo

references to improving or increasing various metrics or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

uphem

-0.77

olina

-0.70

ocument

-0.69

oval

-0.68

plain

-0.65

opus

-0.65

ti

-0.65

©¶æ

-0.65

£ı

-0.63

alin

-0.63

POSITIVE LOGITS

 chances

1.43

 reputation

1.27

 credibility

1.20

 credentials

1.12

 prospects

1.09

 stature

1.08

 spirits

1.06

 fortunes

1.04

 competitiveness

1.03

 morale

1.01

Activations Density 0.218%

action words related to improvement or enhancement

references to improving or increasing various metrics or attributes

No Comments

No Known Activations