INDEX

Explanations

mentions of the word "voter."

oai_token-act-pair · gpt-3.5-turbo

terms related to voters and user engagement in political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

mith

-1.01

uits

-0.96

aurus

-0.94

hift

-0.90

creen

-0.90

chool

-0.90

cale

-0.87

pots

-0.83

ensitive

-0.81

hirt

-0.80

POSITIVE LOGITS

 satisfaction

0.91

hood

0.87

 engagement

0.87

 welfare

0.83

 registrations

0.77

 testimonies

0.77

 participation

0.75

 testim

0.75

 perceptions

0.74

 feedback

0.74

Activations Density 0.195%

mentions of the word "voter."

terms related to voters and user engagement in political contexts

No Comments

No Known Activations