INDEX

Explanations

phrases related to actions or characteristics associated with individuals

oai_token-act-pair · gpt-3.5-turbo

conjugated forms of the verb "to be" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oire

-0.82

osate

-0.77

lag

-0.77

ð

-0.72

lished

-0.71

culosis

-0.70

cture

-0.66

ographer

-0.66

poke

-0.65

orthern

-0.64

POSITIVE LOGITS

 selves

1.07

 themselves

0.99

wolves

0.90

 able

0.86

 outnumbered

0.85

selves

0.85

 interchangeable

0.84

 idiots

0.82

 supposed

0.80

 aware

0.80

Activations Density 0.317%

phrases related to actions or characteristics associated with individuals

conjugated forms of the verb "to be" in various contexts

No Comments

No Known Activations