INDEX

Explanations

numerical values related to quantities or limits

oai_token-act-pair · gpt-3.5-turbo

references to maximum limits on quantities or capacities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

liest

-0.82

govtrack

-0.66

à©

-0.64

pse

-0.58

 disadvant

-0.58

 somew

-0.57

}}}

-0.57

effic

-0.57

_>

-0.57

orically

-0.57

POSITIVE LOGITS

abyte

0.90

 maximum

0.83

 servings

0.81

 consecutive

0.81

 unlimited

0.80

 inclusive

0.78

 Maximum

0.77

maximum

0.77

 qualifying

0.74

 contiguous

0.72

Activations Density 0.232%

numerical values related to quantities or limits

references to maximum limits on quantities or capacities

No Comments

No Known Activations