INDEX

Explanations

discussions related to political accountability and accusations of malfeasance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GraphicsUnit

-0.57

 nahilalakip

-0.55

AutoScale

-0.54

alpha

-0.48

 Alpha

-0.46

rained

-0.43

ikt

-0.43

Kreis

-0.43

 candidate

-0.43

 perifer

-0.42

POSITIVE LOGITS

 House

1.20

House

1.08

 Senate

1.04

 Speaker

1.02

Senate

1.02

 bill

1.01

Speaker

0.99

 parliamentary

0.99

 bills

0.98

 HOUSE

0.93

Activations Density 0.285%

discussions related to political accountability and accusations of malfeasance

No Comments

No Known Activations