INDEX

Explanations

keys and values related to AWS credentials and role assumptions in code snippets

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

//

-0.56

 onPostExecute

-0.55

Xna

-0.54

 onOptions

-0.53

 olympique

-0.53

Akt

-0.53

 istrinya

-0.51

 shopkeeper

-0.51

 messengers

-0.51

 seduced

-0.50

POSITIVE LOGITS

pulumi

0.70

 resource

0.66

Identyfik

0.64

 pulumi

0.60

complexContent

0.55

WithIOException

0.53

coste

0.51

 Resource

0.51

ASTIC

0.50

[--

0.50

Activations Density 0.503%

keys and values related to AWS credentials and role assumptions in code snippets

No Comments

No Known Activations