INDEX

Explanations

abbreviations related to organizational entities

oai_token-act-pair · gpt-3.5-turbo

references to optical character recognition (OCR)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

selves

-0.74

flies

-0.71

dab

-0.68

fuck

-0.67

board

-0.67

things

-0.66

 Hungarian

-0.66

 Friedman

-0.65

gets

-0.65

hak

-0.64

POSITIVE LOGITS

culus

0.96

IAL

0.94

OPS

0.92

aml

0.89

emetery

0.89

ARB

0.88

ategory

0.88

ombat

0.87

ACY

0.86

EED

0.85

Activations Density 0.029%

abbreviations related to organizational entities

references to optical character recognition (OCR)

No Comments

No Known Activations