INDEX

Explanations

occurrences of the word "in" used in various contexts throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

APD

-0.61

neys

-0.61

 raped

-0.60

 overcame

-0.59

 Doodle

-0.58

 alike

-0.57

NOW

-0.56

 thanked

-0.56

soever

-0.56

FTA

-0.56

POSITIVE LOGITS

escap

1.35

humane

1.13

versely

1.11

authent

1.10

accessible

1.07

strument

1.06

 fact

1.04

bred

1.03

ked

1.03

 essence

1.02

Activations Density 0.072%

occurrences of the word "in" used in various contexts throughout the text

No Comments

No Known Activations