INDEX

Explanations

information related to user engagement, feedback, and interaction with digital platforms

oai_token-act-pair · gpt-3.5-turbo

quantitative information about user engagement or participation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rhodes

-0.81

£ı

-0.73

å¦

-0.68

Khe

-0.64

fug

-0.62

 precarious

-0.61

 Hubbard

-0.61

 Sisters

-0.61

 Canaver

-0.60

 Immunity

-0.60

POSITIVE LOGITS

 liking

1.39

 enjoyment

1.20

Reviewer

1.10

 viewer

1.09

 craving

1.07

 appetite

1.06

 consumers

1.06

 buyers

1.04

 buying

1.03

 subscribers

1.02

Activations Density 1.110%

information related to user engagement, feedback, and interaction with digital platforms

quantitative information about user engagement or participation

No Comments

No Known Activations