INDEX

Explanations

acronyms related to organizations or institutions

oai_token-act-pair · gpt-3.5-turbo

references to organizations or entities, particularly those relating to humane societies or health services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

dylib

-0.75

fman

-0.75

 Samoa

-0.74

verages

-0.73

bidden

-0.71

tail

-0.66

oshenko

-0.66

stru

-0.66

taboola

-0.65

ezvous

-0.65

POSITIVE LOGITS

ocial

1.11

HS

1.03

IFT

0.93

Ds

0.92

ospital

0.89

INESS

0.85

BC

0.84

HT

0.84

alez

0.82

EMA

0.82

Activations Density 0.012%

acronyms related to organizations or institutions

references to organizations or entities, particularly those relating to humane societies or health services

No Comments

No Known Activations