INDEX

Explanations

phrases related to medical situations or treatments

oai_token-act-pair · gpt-3.5-turbo

conjunctive phrases and indicators of combinations or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

enhagen

-0.76

AMP

-0.71

 stimulus

-0.69

INTON

-0.68

 Brend

-0.67

TPS

-0.65

Sex

-0.63

 Simulator

-0.63

Sex

-0.63

 Robotics

-0.60

POSITIVE LOGITS

sic

1.12

ensis

0.78

dust

0.78

silver

0.75

edu

0.72

utils

0.72

oult

0.71

tnc

0.71

 slic

0.70

tails

0.69

Activations Density 0.716%

phrases related to medical situations or treatments

conjunctive phrases and indicators of combinations or relationships

No Comments

No Known Activations