INDEX

Explanations

variable names and parameters, particularly those related to counting or indexing in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 autorytatywna

-1.02

 كومونز

-0.85

SourceChecksum

-0.84

IUrlHelper

-0.83

AutoScaleMode

-0.83

RectangleBorder

-0.82

ftagPool

-0.81

MigrationBuilder

-0.79

findpost

-0.79

 الحره

-0.78

POSITIVE LOGITS

0.48

 Comercio

0.40

DebuggerNonUser

0.37

EINVAL

0.37

 desper

0.35

här

0.35

graphicx

0.34

ге

0.32

Activations Density 0.027%

variable names and parameters, particularly those related to counting or indexing in programming contexts

No Comments

No Known Activations