INDEX

Explanations

references to election outcomes and victories

oai_token-act-pair · gpt-3.5-turbo

instances of the word "won" in relation to electoral victories

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

uras

-0.73

IDER

-0.68

Factor

-0.67

 deprecated

-0.66

Root

-0.63

 Redd

-0.62

Redd

-0.61

 Koen

-0.59

MOD

-0.59

 protr

-0.57

POSITIVE LOGITS

 reelection

0.93

election

0.91

 majorities

0.83

elect

0.83

't

0.79

seat

0.76

 elector

0.76

 primaries

0.74

 elections

0.73

 electoral

0.72

Activations Density 0.068%

references to election outcomes and victories

instances of the word "won" in relation to electoral victories

No Comments

No Known Activations