INDEX

Explanations

phrases describing ongoing actions or activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "having" 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

 Regions

-0.61

 premise

-0.59

 Echo

-0.59

 anticipating

-0.58

 invoking

-0.57

 Vehicles

-0.56

 premier

-0.56

 Slovakia

-0.56

 Bolivia

-0.55

ply

-0.55

POSITIVE LOGITS

drawn

1.02

 trouble

0.90

isance

0.86

iculty

0.82

 gotten

0.82

vered

0.80

gotten

0.80

 undergone

0.77

 eaten

0.77

 intercourse

0.77

Activations Density 0.031%

phrases describing ongoing actions or activities

instances of the word "having" in various contexts

No Comments

No Known Activations