INDEX

Explanations

submissions or references related to a specific subject

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Sub" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

OHN

-0.82

Dol

-0.79

ILLE

-0.77

 Cors

-0.77

çİĭ

-0.77

fir

-0.73

GGGG

-0.71

 Zurich

-0.71

 Muse

-0.70

Fra

-0.70

POSITIVE LOGITS

sequent

1.44

mitted

1.43

sequently

1.39

stantial

1.22

verting

1.21

ordinate

1.19

mitting

1.17

jug

1.16

scription

1.15

missive

1.15

Activations Density 0.010%

submissions or references related to a specific subject

occurrences of the word "Sub" in various contexts

No Comments

No Known Activations