INDEX

Explanations

code related to JSON responses and their handling in an API context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 maybe

-1.25

 perhaps

-1.14

 Maybe

-1.04

maybe

-1.00

perhaps

-0.99

 Perhaps

-0.99

Maybe

-0.98

Perhaps

-0.93

 talvez

-0.89

 possibly

-0.85

POSITIVE LOGITS

 Respond

0.76

 respond

0.75

Response

0.71

 Response

0.70

respond

0.68

getResponse

0.68

 responding

0.67

response

0.66

 Responses

0.65

 responds

0.65

Activations Density 0.098%

code related to JSON responses and their handling in an API context

No Comments

No Known Activations