INDEX

Explanations

proper names and specific entities related to culture and medicine

oai_token-act-pair · gpt-3.5-turbo

key terms related to specific individuals or entities associated with a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ired

-0.71

requ

-0.70

ools

-0.70

IRED

-0.68

RIC

-0.67

lot

-0.67

tin

-0.64

rier

-0.64

nic

-0.64

orne

-0.63

POSITIVE LOGITS

oka

1.04

uten

0.85

ĸļ

0.83

 largeDownload

0.74

MV

0.69

ichi

0.69

 stabil

0.68

 Bore

0.66

âĺħâĺħ

0.66

gio

0.66

Activations Density 0.012%

proper names and specific entities related to culture and medicine

key terms related to specific individuals or entities associated with a narrative

No Comments

No Known Activations