INDEX

Explanations

phrases related to physical actions or interactions

oai_token-act-pair · gpt-3.5-turbo

modal verbs indicating ability or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 honoring

-0.68

 honoured

-0.67

 contingency

-0.66

soever

-0.66

ylum

-0.65

 Reserved

-0.65

 Asset

-0.64

 Assignment

-0.64

 Founders

-0.64

 alliances

-0.64

POSITIVE LOGITS

 hear

1.23

 smell

1.19

 detect

1.09

 faintly

1.08

nery

1.04

see

1.04

 barely

1.02

 discern

1.02

 glimpse

1.02

see

1.00

Activations Density 0.138%

phrases related to physical actions or interactions

modal verbs indicating ability or possibility

No Comments

No Known Activations