INDEX

Explanations

mentions of specific instances of medical conditions or incidents

oai_token-act-pair · gpt-3.5-turbo

references to various instances or occurrences of events

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

asus

-0.81

 livest

-0.78

 streng

-0.71

roe

-0.68

oir

-0.65

 monop

-0.64

atomic

-0.64

 embr

-0.64

owered

-0.63

 mathemat

-0.63

POSITIVE LOGITS

 involving

0.98

cases

0.94

 cases

0.92

cale

0.77

0.73

 diagnosed

0.71

uations

0.67

 pregnancies

0.66

backs

0.65

cmp

0.65

Activations Density 0.037%

mentions of specific instances of medical conditions or incidents

references to various instances or occurrences of events

No Comments

No Known Activations