INDEX

Explanations

phrases indicating an action that has not yet occurred or been completed

oai_token-act-pair · gpt-3.5-turbo

instance of the word "yet" indicating unresolved situations or pending outcomes

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

rities

-0.92

sym

-0.84

lav

-0.81

mut

-0.81

regate

-0.79

ructose

-0.78

gencies

-0.77

ritch

-0.76

=#

-0.75

rat

-0.74

POSITIVE LOGITS

 formally

0.91

 officially

0.90

 anymore

0.81

hin

0.78

 RELE

0.78

 fulfilled

0.77

 finalized

0.77

 exists

0.75

 understood

0.74

 settled

0.74

Activations Density 0.022%

phrases indicating an action that has not yet occurred or been completed

instance of the word "yet" indicating unresolved situations or pending outcomes

No Comments

No Known Activations