INDEX

Explanations

phrases containing the word "call" with high activation values

oai_token-act-pair · gpt-3.5-turbo

instances where something is being referred to or named

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ooter

-0.79

ysc

-0.74

earances

-0.69

psons

-0.69

 teasp

-0.69

olith

-0.66

\\\\\\\\

-0.66

lite

-0.66

avy

-0.65

eor

-0.65

POSITIVE LOGITS

 termed

0.76

pires

0.68

Fra

0.68

selves

0.66

called

0.64

 calls

0.63

Fra

0.63

calling

0.62

('

0.61

Activations Density 0.036%

phrases containing the word "call" with high activation values

instances where something is being referred to or named

No Comments

No Known Activations