INDEX

Explanations

instances of the word "wording"

oai_token-act-pair · gpt-3.5-turbo

references to wording and phrasing in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

elsen

-0.80

ept

-0.74

earned

-0.71

ald

-0.70

cot

-0.70

Deg

-0.69

ersen

-0.69

 Democr

-0.68

oy

-0.68

ricular

-0.67

POSITIVE LOGITS

 wording

1.30

 guiActiveUn

1.05

terday

0.80

 instructions

0.75

 typo

0.74

 text

0.72

uggest

0.72

 spelling

0.71

 formulation

0.69

 greeting

0.68

Activations Density 0.010%

instances of the word "wording"

references to wording and phrasing in a document

No Comments

No Known Activations