INDEX

Explanations

phrases related to efficiency and effectiveness

oai_token-act-pair · gpt-3.5-turbo

phrases indicating methods or approaches

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

usters

-1.01

uster

-0.91

itor

-0.82

ĸļ

-0.80

icio

-0.73

aquin

-0.73

ighters

-0.72

aredevil

-0.72

etheus

-0.70

ividual

-0.70

POSITIVE LOGITS

finding

1.01

fare

0.99

LI

0.77

ward

0.77

forward

0.76

PASS

0.75

BOOK

0.72

point

0.70

kell

0.69

Connell

0.69

Activations Density 0.044%

phrases related to efficiency and effectiveness

phrases indicating methods or approaches

No Comments

No Known Activations