INDEX

Explanations

words related to concealing or being elusive

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hide" and its variations in different contexts

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

ctive

-0.86

Ħ¢

-0.84

ombat

-0.76

orough

-0.73

creation

-0.72

urally

-0.71

onia

-0.70

ersive

-0.70

odic

-0.69

 Archdemon

-0.69

POSITIVE LOGITS

ously

1.07

 behind

0.92

away

0.87

rets

0.77

 hide

0.76

hid

0.73

 hiding

0.72

 underneath

0.72

 contr

0.69

buster

0.68

Activations Density 0.029%

words related to concealing or being elusive

instances of the word "hide" and its variations in different contexts

No Comments

No Known Activations