INDEX

Explanations

mentions of political figures, specifically the President

oai_token-act-pair · gpt-3.5-turbo

mentions of the President and related titles

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

rows

-0.81

toggle

-0.76

lin

-0.71

ĻĤ

-0.71

 dent

-0.70

iannopoulos

-0.67

roman

-0.66

 newcomers

-0.66

 scanners

-0.64

tac

-0.63

POSITIVE LOGITS

 Accountability

0.96

 Manager

0.90

 Coordinator

0.89

 Party

0.88

 Registry

0.86

 Graveyard

0.85

 Himself

0.85

 Candidate

0.81

 Officer

0.81

 Agent

0.80

Activations Density 0.154%

mentions of political figures, specifically the President

mentions of the President and related titles

No Comments

No Known Activations