INDEX

Explanations

instances of the word "here" in a sentence

oai_token-act-pair · gpt-3.5-turbo

instances of the word "here" and its variations

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

asting

-0.61

estinal

-0.61

 absorbing

-0.60

-0.58

Inf

-0.55

 prominently

-0.55

jug

-0.55

oppable

-0.55

 gripping

-0.54

 hurd

-0.54

POSITIVE LOGITS

abouts

1.24

upon

1.24

tics

1.13

fore

1.07

tical

1.03

iton

0.92

ttes

0.86

ford

0.82

tic

0.81

backer

0.81

Activations Density 0.021%

instances of the word "here" in a sentence

instances of the word "here" and its variations

No Comments

No Known Activations