INDEX

Explanations

numerical values and expressions related to data structures or programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

antMatchers

-0.85

حياتها

-0.81

حياته

-0.77

 Weis

-0.70

 Weiss

-0.68

ParallelGroup

-0.67

MessageState

-0.66

Cyfeiriadau

-0.66

 Tully

-0.66

 jLabel

-0.65

POSITIVE LOGITS

↵↵

0.77

principalTable

0.75

<eos>

0.71

<tr>

0.69

setVerticalGroup

0.66

<h2>

0.64

</table>

0.63

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.63

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.61

 gekomen

0.61

Activations Density 0.135%

numerical values and expressions related to data structures or programming constructs

No Comments

No Known Activations