INDEX

Explanations

references to specific locations, construction methods, and entity relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 springfox

-0.60

\{\\

-0.55

fulness

-0.54

 Familienname

-0.52

Portale

-0.51

InstrumentedTest

-0.50

Slf

-0.49

 között

-0.45

 PeEnEo

-0.45

 thought

-0.45

POSITIVE LOGITS

Vidu

0.67

]--;

0.64

dorfer

0.62

 jsPsych

0.62

 actionMode

0.61

 AssemblyProduct

0.58

 betweenstory

0.58

naphthal

0.57

 فريبيس

0.55

__':

0.55

Activations Density 1.261%

references to specific locations, construction methods, and entity relationships

No Comments

No Known Activations