INDEX

Explanations

terms related to minimalism

oai_token-act-pair · gpt-3.5-turbo

references to minimalism

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

lyn

-0.73

Report

-0.72

Sah

-0.70

ravings

-0.67

dor

-0.65

Phill

-0.65

uay

-0.65

Queen

-0.65

Gener

-0.65

RAFT

-0.64

POSITIVE LOGITS

istic

1.12

istically

0.99

etheless

0.99

 amount

0.94

ism

0.89

izes

0.88

ocre

0.87

isite

0.86

 amounts

0.84

 effort

0.84

Activations Density 0.015%

terms related to minimalism

references to minimalism

No Comments

No Known Activations