INDEX

Explanations

mentions of approval ratings in political contexts

oai_token-act-pair · gpt-3.5-turbo

references to approval ratings of political figures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utical

-0.75

aer

-0.68

 Roche

-0.62

 fixme

-0.61

portation

-0.61

 manufact

-0.60

adr

-0.59

Alz

-0.59

 Flam

-0.59

lla

-0.59

POSITIVE LOGITS

 ratings

1.45

 rating

1.43

Rating

1.14

 Rating

1.12

 Ratings

1.01

 Gallup

1.01

 majorities

0.99

rating

0.98

 polls

0.92

 polled

0.92

Activations Density 0.071%

mentions of approval ratings in political contexts

references to approval ratings of political figures

No Comments

No Known Activations