INDEX

Explanations

politicians' names preceded by their title 'Rep.'

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of representatives and their associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 commercially

-0.79

ahime

-0.72

istically

-0.69

zb

-0.69

obyl

-0.67

 traffickers

-0.66

 civilisation

-0.66

oscope

-0.65

 maturity

-0.64

 economically

-0.63

POSITIVE LOGITS

 Patrick

0.95

Patrick

0.93

 Darrell

0.91

 Michele

0.88

Ted

0.86

PAC

0.85

 Louie

0.84

 Tuls

0.84

 Mario

0.84

osponsors

0.84

Activations Density 0.037%

politicians' names preceded by their title 'Rep.'

repeated mentions of representatives and their associations

No Comments

No Known Activations