INDEX

Explanations

symbols or terms related to mathematical or logical structures

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

 getItemId

-1.03

Hentet

-1.01

enumi

-0.98

tvguidetime

-0.96

IUrlHelper

-0.94

 kaynağından

-0.92

 MainAxisSize

-0.91

 onAnimation

-0.89

ViewImports

-0.87

MockMvc

-0.87

POSITIVE LOGITS

1.00

0.94

the

0.68

0.65

0.61

away

0.60

AWAY

0.58

til

0.58

0.57

es

0.53

Activations Density 0.256%

symbols or terms related to mathematical or logical structures

No Comments

No Known Activations