INDEX

Explanations

scientific and technical terms related to nuclear reactions

oai_token-act-pair · gpt-3.5-turbo

scientific terms related to nuclear physics and research

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

 symp

-0.70

 fitting

-0.60

 psychiat

-0.59

 timely

-0.58

reau

-0.57

 widest

-0.57

 trout

-0.57

rency

-0.56

 answ

-0.56

 skelet

-0.56

POSITIVE LOGITS

aneous

0.90

SQL

0.87

culosis

0.86

âĶĢâĶĢâĶĢâĶĢ

0.77

à¼

0.76

ogo

0.70

È

0.69

ution

0.68

inous

0.67

aneously

0.66

Activations Density 0.252%

scientific and technical terms related to nuclear reactions

scientific terms related to nuclear physics and research

No Comments

No Known Activations