INDEX

Explanations

DSM codes and related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of diagnostic or reference codes related to mental health disorders

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

swick

-0.82

Reviewer

-0.72

============

-0.69

staking

-0.67

issance

-0.67

 symmetry

-0.66

ufact

-0.66

ishable

-0.66

uters

-0.65

========

-0.63

POSITIVE LOGITS

IFF

1.09

omething

1.02

OME

0.97

DK

0.93

FW

0.90

WD

0.90

LR

0.90

yll

0.88

ICT

0.87

VI

0.86

Activations Density 0.028%

DSM codes and related terms

mentions of diagnostic or reference codes related to mental health disorders

No Comments

No Known Activations