INDEX

Explanations

phrases indicating agreement or reliability

oai_token-act-pair · gpt-3.5-turbo

instances of the word "upon" and related prepositions or phrases that signify conditions or agreements

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

adelphia

-0.62

letters

-0.61

obal

-0.60

liction

-0.59

ARS

-0.58

raph

-0.58

Links

-0.57

credit

-0.57

 Clicker

-0.57

Moon

-0.57

POSITIVE LOGITS

ãĤ´ãĥ³

0.84

itech

0.70

ĸļ

0.70

by

0.70

BY

0.62

EStream

0.59

 offline

0.58

.–

0.58

uchin

0.58

 Giul

0.58

Activations Density 0.196%

phrases indicating agreement or reliability

instances of the word "upon" and related prepositions or phrases that signify conditions or agreements

No Comments

No Known Activations