INDEX

Explanations

strong verbs or nouns ending in '-ing'

oai_token-act-pair · gpt-3.5-turbo

words that suggest strength or robustness

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

 drum

-0.72

 stink

-0.71

spin

-0.70

 dust

-0.69

 fever

-0.68

 rift

-0.67

 fuss

-0.66

 sweat

-0.65

 spin

-0.64

 trump

-0.63

POSITIVE LOGITS

itionally

1.06

ations

1.06

ivably

1.04

ational

1.01

atic

0.99

itably

0.98

ATIONS

0.96

ances

0.96

atically

0.93

aci

0.93

Activations Density 0.155%

strong verbs or nouns ending in '-ing'

words that suggest strength or robustness

No Comments

No Known Activations