INDEX

Explanations

code structures related to data parsing and decoding operations

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

decoding JSON strings

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 oprot

-0.61

 pinulongan

-0.59

ConstraintMaker

-0.56

writeFieldEnd

-0.52

featureID

-0.49

ismet

-0.49

Географиясе

-0.49

 arşivlendi

-0.49

ContentAlignment

-0.47

TypedDataSet

-0.46

POSITIVE LOGITS

decode

0.77

 decode

0.68

 decoding

0.64

 Decode

0.63

Decode

0.59

 decoded

0.58

 decipher

0.58

Decoder

0.58

 Decoder

0.58

Decoding

0.57

Activations Density 0.044%

code structures related to data parsing and decoding operations

decoding JSON strings

No Comments

No Known Activations