INDEX

Explanations

specific locations or sources mentioned in text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "here."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

visors

-0.67

itialized

-0.63

omore

-0.62

usterity

-0.62

iven

-0.60

 judgement

-0.58

 Dungeons

-0.58

Zen

-0.56

ãĥı

-0.55

 parap

-0.54

POSITIVE LOGITS

abouts

1.22

tics

1.19

tical

1.17

tic

1.04

ridges

0.77

with

0.74

here

0.73

edin

0.73

rolet

0.72

 guiActiveUn

0.70

Activations Density 0.042%

specific locations or sources mentioned in text

instances of the word "here."

No Comments

No Known Activations