INDEX

Explanations

scientific terms and acronyms related to biological pathways and processes

oai_token-act-pair · gpt-3.5-turbo

occurrences of negative expressions or terms related to various biological mechanisms

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ulhu

-0.87

 Polk

-0.80

essee

-0.79

Wiz

-0.78

ãģ®å®

-0.75

 Stranger

-0.73

 Jimmy

-0.73

Ĥª

-0.71

 Vaughn

-0.71

 Borders

-0.70

POSITIVE LOGITS

induced

1.31

mediated

1.28

derived

1.21

containing

1.18

bearing

1.15

based

1.13

shaped

1.12

dependent

1.09

treated

1.08

specific

1.06

Activations Density 0.182%

scientific terms and acronyms related to biological pathways and processes

occurrences of negative expressions or terms related to various biological mechanisms

No Known Activations