INDEX

Explanations

quantitative comparisons involving inequalities

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

le followed by i, j, c, n, pool, Agency, Elementary

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 initComponents

-0.70

__*/

-0.68

RegressionTest

-0.66

 &___

-0.64

transQ

-0.64

 AssemblyVersion

-0.60

uxxxx

-0.60

 محفوظة

-0.60

BackPressed

-0.59

EndGlobalSection

-0.57

POSITIVE LOGITS

le

2.56

LE

1.88

Le

1.11

le

1.06

lele

1.04

LE

1.00

Le

0.99

leu

0.87

ле

0.87

leth

0.86

Activations Density 0.016%

quantitative comparisons involving inequalities

le followed by i, j, c, n, pool, Agency, Elementary

No Comments

No Known Activations