INDEX

Explanations

terms related to computer programming and submodules

oai_token-act-pair · gpt-3.5-turbo

references to various submodules or components in a technical context

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

ILLE

-0.85

 Qiao

-0.82

Ö¼

-0.77

 Gael

-0.75

ORED

-0.74

OHN

-0.73

 Zurich

-0.72

assetsadobe

-0.72

 Lauder

-0.72

FORE

-0.72

POSITIVE LOGITS

missive

1.33

mitter

1.22

sequent

1.16

ordinate

1.16

species

1.11

mers

1.10

atomic

1.09

sequently

1.09

verting

1.08

classes

1.07

Activations Density 0.014%

terms related to computer programming and submodules

references to various submodules or components in a technical context

No Comments

No Known Activations