INDEX

Explanations

phrases related to representation or symbolization

oai_token-act-pair · gpt-3.5-turbo

references to representation and authority 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tun

-0.64

 bombs

-0.62

 dazz

-0.62

 assum

-0.60

iously

-0.58

 publishes

-0.58

 ignition

-0.58

 Nightmares

-0.57

bomb

-0.57

 Nikol

-0.57

POSITIVE LOGITS

 pinnacle

0.84

 constituents

0.76

 interests

0.76

Interstitial

0.76

OPLE

0.74

 culmination

0.72

opian

0.71

utral

0.70

POS

0.69

 widest

0.68

Activations Density 0.153%

phrases related to representation or symbolization

references to representation and authority in various contexts

No Comments

No Known Activations