INDEX

Explanations

statements or opinions expressed by individuals or groups

oai_token-act-pair · gpt-3.5-turbo

instances of the word "saying" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

estern

-0.92

visible

-0.78

peg

-0.75

ocument

-0.73

PokÃ©

-0.73

\/\/

-0.72

gomery

-0.70

esc

-0.70

transfer

-0.70

èª

-0.69

POSITIVE LOGITS

 ISPs

0.66

 they

0.66

it

0.65

 goodbye

0.64

'[

0.63

 apart

0.61

"[

0.60

 abusers

0.59

 constituents

0.57

Af

0.57

Activations Density 0.076%

statements or opinions expressed by individuals or groups

instances of the word "saying" in various contexts

No Comments

No Known Activations