INDEX

Explanations

phrases related to politics and policies, particularly focused on healthcare and government programs

oai_token-act-pair · gpt-3.5-turbo

references to political and legislative issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ui

-0.73

iri

-0.68

cil

-0.63

antz

-0.62

iazep

-0.62

iple

-0.61

edi

-0.60

 pengu

-0.59

actic

-0.58

Yi

-0.58

POSITIVE LOGITS

whatever

0.64

 overseen

0.64

 Digest

0.63

TPP

0.59

dq

0.59

 ObamaCare

0.58

 itself

0.57

despite

0.57

atron

0.56

 guaranteeing

0.56

Activations Density 0.760%

phrases related to politics and policies, particularly focused on healthcare and government programs

references to political and legislative issues

No Comments

No Known Activations