INDEX

Explanations

past tense verbs related to job-related activities

oai_token-act-pair · gpt-3.5-turbo

verbs that describe states of being or existence

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

 oneself

-0.83

icans

-0.75

 Franch

-0.72

orks

-0.71

gap

-0.69

heny

-0.69

asio

-0.68

 Awakens

-0.68

aqu

-0.67

verts

-0.65

POSITIVE LOGITS

 priceless

0.78

 dwindling

0.72

 accordingly

0.71

 bona

0.70

 theirs

0.69

 blown

0.69

 counterparts

0.68

 indistinguishable

0.67

 invaluable

0.67

 hers

0.66

Activations Density 0.445%

past tense verbs related to job-related activities

verbs that describe states of being or existence

No Comments

No Known Activations