INDEX

Explanations

terms related to data reconstruction and attributes associated with various locations or contexts

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

 Sorensen

-0.89

/\.

-0.84

 Slag

-0.84

Linq

-0.84

 rval

-0.74

ctools

-0.74

 Macht

-0.73

 Lover

-0.72

[]:

-0.72

 Игорь

-0.72

POSITIVE LOGITS

 Colette

0.74

 Puck

0.73

 estadual

0.73

Aub

0.71

icoot

0.69

 Arrow

0.69

 Axiom

0.69

Puck

0.68

 Pollack

0.68

FTC

0.67

Activations Density 2.369%

terms related to data reconstruction and attributes associated with various locations or contexts

No Comments

No Known Activations