INDEX

Explanations

adjectives relating to strictness

oai_token-act-pair · gpt-3.5-turbo

instances of the word "strict" 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 @ 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

ilater

-0.93

igate

-0.83

assies

-0.81

********

-0.79

ovember

-0.72

FORE

-0.71

****

-0.70

****************

-0.70

ufact

-0.70

xxxxxxxx

-0.70

POSITIVE LOGITS

 adherence

1.13

ures

1.12

ness

1.03

 strict

0.95

nesses

0.93

 scrutiny

0.86

 criteria

0.83

est

0.83

 adherent

0.81

 restrictive

0.81

Activations Density 0.020%

adjectives relating to strictness

instances of the word "strict" in various contexts

No Comments

No Known Activations