INDEX

Explanations

phrases related to actions performed by individuals

oai_token-act-pair · gpt-3.5-turbo

phrases related to actions and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Entered

-0.71

 suspects

-0.69

Board

-0.66

ussen

-0.62

assis

-0.60

 Flood

-0.59

inently

-0.58

 Dram

-0.57

 Rampage

-0.57

 Gork

-0.57

POSITIVE LOGITS

pez

1.06

 differently

0.94

 wrong

0.84

 unconsciously

0.80

actic

0.74

Äĩ

0.73

wrong

0.72

 administr

0.72

 athlet

0.70

å¥³

0.69

Activations Density 0.050%

phrases related to actions performed by individuals

phrases related to actions and accountability

No Comments

No Known Activations