INDEX

Explanations

words related to job performance and responsibilities

oai_token-act-pair · gpt-3.5-turbo

references to responsibility and performance of tasks

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

glas

-0.80

urated

-0.75

lished

-0.70

ONSORED

-0.69

razil

-0.68

 Flavoring

-0.66

artment

-0.64

incible

-0.63

eele

-0.62

 Scythe

-0.62

POSITIVE LOGITS

 same

0.93

 utmost

0.93

same

0.88

 justice

0.87

 homework

0.84

 injustice

0.81

 usual

0.80

 best

0.79

 chores

0.73

oret

0.70

Activations Density 0.107%

words related to job performance and responsibilities

references to responsibility and performance of tasks

No Comments

No Known Activations