INDEX

Explanations

instances where something is physically or metaphorically getting closer or near to something else

oai_token-act-pair · gpt-3.5-turbo

references to proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilts

-0.63

NZ

-0.62

dor

-0.61

fre

-0.59

anity

-0.58

hal

-0.58

Games

-0.56

STE

-0.56

odan

-0.54

NT

-0.53

POSITIVE LOGITS

 proximity

0.97

 thereto

0.96

together

0.93

 toget

0.91

 together

0.91

to

0.83

 resemblance

0.82

 confines

0.81

 resemble

0.79

 scrutiny

0.77

Activations Density 0.033%

instances where something is physically or metaphorically getting closer or near to something else

references to proximity or closeness

No Comments

No Known Activations