INDEX

Explanations

instances of double-checking or re-evaluating in a text

oai_token-act-pair · gpt-3.5-turbo

terms related to verification and validation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

strong

-0.70

SEE

-0.68

margin

-0.63

VA

-0.63

POST

-0.61

Church

-0.61

QUI

-0.60

je

-0.59

benefit

-0.59

Scot

-0.59

POSITIVE LOGITS

ibly

0.85

 animations

0.77

edIn

0.75

 THEM

0.75

edly

0.73

rarily

0.72

 versions

0.72

ify

0.72

lished

0.70

atures

0.69

Activations Density 0.245%

instances of double-checking or re-evaluating in a text

terms related to verification and validation processes

No Comments

No Known Activations