INDEX

Explanations

scientific information related to the composition of materials or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "composed"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

arthy

-0.75

hawks

-0.73

adesh

-0.69

TPP

-0.69

ery

-0.68

orthy

-0.67

itual

-0.62

mere

-0.61

WT

-0.61

 Trials

-0.61

POSITIVE LOGITS

ertodd

0.89

nces

0.83

mble

0.81

 composing

0.80

 composed

0.79

 entirely

0.75

 solely

0.73

 compositions

0.73

getic

0.73

âĶģ

0.72

Activations Density 0.018%

scientific information related to the composition of materials or entities

occurrences of the word "composed"

No Comments

No Known Activations