INDEX

Explanations

words related to work and workplace situations

oai_token-act-pair · gpt-3.5-turbo

high-frequency or notable introductory phrases and specific characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

raints

-0.77

luster

-0.66

ecided

-0.63

terday

-0.62

nesday

-0.61

chuk

-0.61

 outwe

-0.60

coni

-0.59

abwe

-0.58

ierrez

-0.58

POSITIVE LOGITS

 largeDownload

0.75

 âĢº

0.62

;;;;;;;;;;;;

0.61

 Profile

0.60

 Gets

0.60

 Â·

0.58

 Sphere

0.58

ega

0.58

 Files

0.57

 WATCHED

0.57

Activations Density 0.113%

words related to work and workplace situations

high-frequency or notable introductory phrases and specific characters

No Comments

No Known Activations