INDEX

Explanations

references to the Democratic National Committee (DNC)

oai_token-act-pair · gpt-3.5-turbo

mentions of the Democratic National Committee (DNC) and its activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Kubrick

-0.81

 Kafka

-0.73

otropic

-0.73

...]

-0.72

 Shinji

-0.71

 Conan

-0.69

Ibn

-0.69

ãĤ¹ãĥĪ

-0.68

gered

-0.68

 Britann

-0.67

POSITIVE LOGITS

Leaks

0.90

 Chair

0.88

 chair

0.87

olicy

0.85

agogue

0.84

DNC

0.82

CCC

0.82

ilion

0.81

 staffer

0.80

iversity

0.76

Activations Density 0.017%

references to the Democratic National Committee (DNC)

mentions of the Democratic National Committee (DNC) and its activities

No Comments

No Known Activations