INDEX

Explanations

words relating to spatial locations or positions

oai_token-act-pair · gpt-3.5-turbo

prepositions and conjunctions indicating relationships or positional 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

 answ

-0.72

 referen

-0.64

 apologizing

-0.64

 furthermore

-0.63

OUP

-0.63

warn

-0.62

 moreover

-0.61

 lineback

-0.61

ritical

-0.61

redibly

-0.61

POSITIVE LOGITS

aband

0.79

urned

0.67

edge

0.64

Pop

0.64

hops

0.63

pole

0.62

igate

0.62

 weddings

0.62

ses

0.61

iped

0.60

Activations Density 0.528%

words relating to spatial locations or positions

prepositions and conjunctions indicating relationships or positional contexts

No Comments

No Known Activations