INDEX

Explanations

phrases related to job positions or levels

oai_token-act-pair · gpt-3.5-turbo

terms related to entry-level positions or roles

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

awar

-0.72

 tremend

-0.70

cale

-0.68

 Parables

-0.66

 opio

-0.66

gans

-0.65

kos

-0.62

 mamm

-0.62

 Band

-0.62

 Carth

-0.61

POSITIVE LOGITS

prise

0.98

apore

0.89

prises

0.85

prising

0.85

lude

0.83

tain

0.83

tainment

0.79

 entry

0.77

 INTO

0.77

TRY

0.76

Activations Density 0.025%

phrases related to job positions or levels

terms related to entry-level positions or roles

No Comments

No Known Activations