INDEX

Explanations

mentions of political nominees, particularly the word "nominee."

oai_token-act-pair · gpt-3.5-turbo

references to political nominees, particularly in the context of elections

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iple

-0.77

Ku

-0.74

utenberg

-0.72

²¾

-0.70

doors

-0.70

 Spiegel

-0.69

MpServer

-0.69

pir

-0.69

stra

-0.68

GER

-0.67

POSITIVE LOGITS

 nominee

0.95

 nominees

0.92

 candidate

0.75

 nomination

0.74

Nom

0.74

 TRUMP

0.72

 Candidate

0.69

 Memor

0.69

 nominated

0.67

 Donald

0.66

Activations Density 0.012%

mentions of political nominees, particularly the word "nominee."

references to political nominees, particularly in the context of elections

No Comments

No Known Activations