INDEX

Explanations

names of political figures

oai_token-act-pair · gpt-3.5-turbo

references to specific political figures or candidates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

fulness

-0.79

½

-0.76

worthiness

-0.75

PET

-0.75

 charism

-0.74

ework

-0.74

aways

-0.71

ESA

-0.69

ãģ¦

-0.67

 Smoking

-0.67

POSITIVE LOGITS

 Ellison

1.04

urations

0.78

eering

0.77

irez

0.76

entanyl

0.74

ermott

0.64

igible

0.63

 caucuses

0.62

imore

0.60

 Franken

0.60

Activations Density 0.013%

names of political figures

references to specific political figures or candidates

No Comments

No Known Activations