INDEX

Explanations

words related to data or information

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "ont" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BILITIES

-0.82

loo

-0.76

GBT

-0.72

ulative

-0.71

tips

-0.71

GY

-0.70

glers

-0.68

DOM

-0.67

FFER

-0.67

MU

-0.67

POSITIVE LOGITS

gomery

1.01

osaurus

0.97

ario

0.95

rol

0.93

ological

0.92

ainment

0.90

ology

0.88

aire

0.87

ract

0.86

ribut

0.84

Activations Density 0.017%

words related to data or information

the presence of the word "ont" in various contexts

No Comments

No Known Activations