INDEX

Explanations

references to quantitative data or measurements

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

The neuron detects words related to data, information, and evidence, particularly in formal or technical contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

nouns referring to collections of data, information, or measurements.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

opedia

-0.42

 élas

-0.40

 ainfi

-0.39

ANTLR

-0.35

baron

-0.35

[]:

-0.35

 reelection

-0.32

Accès

-0.32

 réflex

-0.32

->___

-0.32

POSITIVE LOGITS

put

0.72

 selected

0.71

 chosen

0.71

 released

0.71

 taken

0.70

 retained

0.68

 adopted

0.68

 brought

0.66

 examined

0.66

 reported

0.65

Activations Density 1.091%

references to quantitative data or measurements

The neuron detects words related to data, information, and evidence, particularly in formal or technical contexts.

nouns referring to collections of data, information, or measurements.

No Comments

No Known Activations