INDEX

Explanations

references to columns in a dataset or table format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

SpringRunner

-0.59

 Rinehart

-0.57

anță

-0.57

Filmografie

-0.56

ύ

-0.54

----</

-0.54

magna

-0.52

rippa

-0.52

leetcode

-0.49

ுக

-0.49

POSITIVE LOGITS

col

2.08

col

2.04

Col

1.83

coll

1.66

Col

1.66

 Coll

1.60

Coll

1.57

COL

1.52

 coll

1.50

COLL

1.46

Activations Density 0.113%

references to columns in a dataset or table format

No Comments

No Known Activations