INDEX

Explanations

references to the word "ink"

oai_token-act-pair · gpt-3.5-turbo

references to the word "ink" 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 @ 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

ADS

-0.70

cffffcc

-0.69

PsyNetMessage

-0.64

 detrim

-0.64

 Valkyrie

-0.62

 Roads

-0.61

ideos

-0.61

nels

-0.60

 wreck

-0.60

CVE

-0.59

POSITIVE LOGITS

jet

1.09

manship

0.98

ink

0.97

lings

0.94

 cartridges

0.94

prints

0.93

clip

0.89

sworth

0.85

matic

0.80

atha

0.80

Activations Density 0.032%

references to the word "ink"

references to the word "ink" in various contexts

No Comments

No Known Activations