INDEX

Explanations

instances of the phrase "in the first place."

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "first" 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 @ 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

apego

-0.74

uties

-0.70

 staples

-0.66

othing

-0.65

paio

-0.65

ourge

-0.63

 faults

-0.61

rish

-0.60

ocide

-0.60

 brakes

-0.60

POSITIVE LOGITS

 nutshell

0.99

 vicinity

0.98

 guise

0.92

 vein

0.87

 midst

0.84

 manner

0.83

 context

0.82

 courtyard

0.80

 hurry

0.78

ixties

0.77

Activations Density 0.145%

instances of the phrase "in the first place."

references to the concept of "first" in various contexts

No Comments

No Known Activations