INDEX

Explanations

code snippets and programming-related logic within a larger document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

<eos>

-0.72

OCCURRED

-0.54

↵↵

-0.50

providedIn

-0.49

writeFieldEnd

-0.49

Ecotoxicity

-0.45

↵↵↵

-0.45

mouseout

-0.43

cinogen

-0.43

励

-0.43

POSITIVE LOGITS

enterOuterAlt

0.86

AddTagHelper

0.84

SequentialGroup

0.77

 auroit

0.75

FieldBuilder

0.73

WithIOException

0.69

RenderAtEndOf

0.67

 feroit

0.67

ItemBackground

0.66

Efq

0.66

Activations Density 0.233%

code snippets and programming-related logic within a larger document

No Comments

No Known Activations