INDEX

Explanations

mentions of political figures and activities

oai_token-act-pair · gpt-3.5-turbo

discussions related to political actions and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tyre

-0.94

 tyres

-0.90

celona

-0.87

teness

-0.80

 Notting

-0.79

 catalogue

-0.78

 fuelled

-0.78

Buyable

-0.76

borgh

-0.74

 recognise

-0.74

POSITIVE LOGITS

 Senators

2.07

 senators

2.07

 Senate

1.98

Senate

1.91

 Senator

1.72

 McConnell

1.69

Senator

1.67

Sen

1.64

 Congressional

1.63

 Schumer

1.63

Activations Density 0.550%

mentions of political figures and activities

discussions related to political actions and events

No Comments

No Known Activations