INDEX

Explanations

instances of the word "look" with other related words

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "look at" followed by related observations or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

burgh

-0.66

atile

-0.63

ERN

-0.61

Es

-0.61

phrine

-0.61

Ts

-0.60

keeper

-0.59

ensed

-0.58

Â¯Â¯Â¯Â¯

-0.58

ilib

-0.58

POSITIVE LOGITS

»Ĵ

0.78

facts

0.78

Statistics

0.71

herer

0.70

rael

0.70

¿½

0.68

Compare

0.67

 Piper

0.67

ĳå£«

0.67

 anecd

0.66

Activations Density 0.141%

instances of the word "look" with other related words

instances of the phrase "look at" followed by related observations or analyses

No Comments

No Known Activations