INDEX

Explanations

verbs that indicate obtaining or originating something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "derive" and its variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mouth

-0.81

roller

-0.78

mir

-0.76

eden

-0.75

phis

-0.74

shr

-0.71

rooms

-0.65

ennett

-0.65

eye

-0.65

 Camer

-0.65

POSITIVE LOGITS

 derive

0.84

 derived

0.82

çīĪ

0.81

itives

0.77

minist

0.77

 deriv

0.75

iable

0.72

uced

0.72

 amusement

0.71

LECT

0.70

Activations Density 0.042%

verbs that indicate obtaining or originating something

instances of the word "derive" and its variations

No Comments

No Known Activations