INDEX

Explanations

phrases related to productivity or output

oai_token-act-pair · gpt-3.5-turbo

terms related to yielding or producing outcomes, particularly in financial or resource 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

hemat

-0.66

tox

-0.64

zai

-0.63

 compuls

-0.62

ype

-0.61

aldo

-0.59

hemy

-0.59

 scapego

-0.58

alg

-0.58

ocal

-0.58

POSITIVE LOGITS

 yield

1.03

 yields

0.92

 yielding

0.83

ENCY

0.83

bang

0.76

 yielded

0.71

plings

0.69

uces

0.68

onse

0.68

ensical

0.68

Activations Density 0.021%

phrases related to productivity or output

terms related to yielding or producing outcomes, particularly in financial or resource contexts

No Comments

No Known Activations