INDEX

Explanations

words related to proteins and their functions or consumption

oai_token-act-pair · gpt-3.5-turbo

references to different types of proteins

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

sbm

-0.67

 Fantasy

-0.67

orld

-0.66

rolet

-0.66

 Noon

-0.65

 Moff

-0.63

 Fargo

-0.63

ragon

-0.62

 Faust

-0.62

POSITIVE LOGITS

aceous

1.22

 isolate

0.99

rotein

0.97

zyme

0.93

protein

0.93

 powd

0.93

 protein

0.86

acid

0.85

 synthesis

0.83

 phosphate

0.83

Activations Density 0.012%

words related to proteins and their functions or consumption

references to different types of proteins

No Comments

No Known Activations