INDEX

Explanations

terms related to psychoactive substances and medical conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to psychoactive substances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

HCR

-0.76

urat

-0.76

MENTS

-0.75

ICAN

-0.74

UAL

-0.72

RL

-0.71

erous

-0.69

swick

-0.68

UES

-0.68

Newsletter

-0.67

POSITIVE LOGITS

analysis

0.98

 psycho

0.98

ises

0.90

active

0.85

 absor

0.83

ega

0.82

igmatic

0.76

acs

0.70

osis

0.70

 analyse

0.69

Activations Density 0.012%

terms related to psychoactive substances and medical conditions

terms related to psychoactive substances

No Comments

No Known Activations