INDEX

Explanations

instances where something has already been done or is in place

oai_token-act-pair · gpt-3.5-turbo

references to the concept of something being "already" established or existing

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

case

-0.84

istics

-0.79

udge

-0.79

rary

-0.75

rent

-0.71

ueller

-0.69

rus

-0.68

orie

-0.67

rarily

-0.67

onnaissance

-0.66

POSITIVE LOGITS

 underway

0.89

 existed

0.84

 exists

0.84

 surpassed

0.81

 begun

0.76

 knew

0.76

 fulfilled

0.76

 booked

0.73

 served

0.73

 racked

0.73

Activations Density 0.032%

instances where something has already been done or is in place

references to the concept of something being "already" established or existing

No Comments

No Known Activations