INDEX

Explanations

conjunctions and transitional phrases that indicate relationships and conditions in arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cov

-0.68

ãĥĦ

-0.61

ãĤ¨ãĥ«

-0.58

 blitz

-0.57

 equivalents

-0.57

 hect

-0.54

 horizont

-0.54

 menace

-0.53

 warp

-0.52

 ensu

-0.52

POSITIVE LOGITS

ople

0.76

ummer

0.73

undai

0.73

amaz

0.68

uckle

0.66

ever

0.66

immers

0.65

issan

0.64

immer

0.63

uzz

0.61

Activations Density 0.233%

conjunctions and transitional phrases that indicate relationships and conditions in arguments

No Comments

No Known Activations