INDEX

Explanations

specific structure or formatting patterns in code-related text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

LEncoder

-0.66

 "..\..\..\

-0.64

roffen

-0.62

]-'

-0.60

ModelAdmin

-0.59

UserScript

-0.59

zunehmen

-0.59

}{@

-0.57

PerformLayout

-0.57

piecze

-0.57

POSITIVE LOGITS

case

0.97

 case

0.96

Case

0.75

 cases

0.71

CASE

0.70

 Case

0.70

 CASE

0.64

cases

0.64

 geval

0.60

 caso

0.59

Activations Density 0.069%

specific structure or formatting patterns in code-related text

No Comments

No Known Activations