INDEX

Explanations

phrases related to accountability in law enforcement

oai_token-act-pair · gpt-3.5-turbo

terms related to specific individuals and entities linked to significant events or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 resid

-0.76

ĸļ

-0.70

 coli

-0.63

pole

-0.61

ipel

-0.61

 experien

-0.59

Db

-0.59

ãĥīãĥ©ãĤ´ãĥ³

-0.59

 Cipher

-0.59

mosp

-0.58

POSITIVE LOGITS

anni

0.87

arest

0.70

amic

0.69

illet

0.68

 spilled

0.68

anamo

0.66

afort

0.62

agall

0.61

 Qiao

0.61

ilipp

0.60

Activations Density 0.262%

phrases related to accountability in law enforcement

terms related to specific individuals and entities linked to significant events or issues

No Comments

No Known Activations