INDEX

Explanations

bullet points and list formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Bronnen

-0.77

GeoNames

-0.72

 GenerationType

-0.69

 esternos

-0.66

 validamos

-0.66

BagLayout

-0.66

 MessageBoxIcon

-0.65

DebuggerNonUser

-0.64

 فريبيس

-0.63

 createSlice

-0.61

POSITIVE LOGITS

1.04

//*

0.93

 }^{*}$

0.77

 <<<<<<<<<<<<<<

0.73

|*

0.72

The

0.71

$*$

0.70

()*

0.69

*]

0.69

*=

0.68

Activations Density 0.042%

bullet points and list formatting

No Comments

No Known Activations