INDEX

Explanations

words related to requests and their handling in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

<strong>

-0.85

<em>

-0.83

----------------

-0.81

<sup>

-0.62

 fVar

-0.61

 Usher

-0.61

乐

-0.60

forRoot

-0.60

<b>

-0.60

POSITIVE LOGITS

req

1.19

req

1.11

kPa

0.93

ScopeManager

0.92

Ctx

0.91

REQ

0.90

AddTagHelper

0.90

__":

0.90

__':

0.88

︎

0.87

Activations Density 0.089%

words related to requests and their handling in a programming context

No Comments

No Known Activations