INDEX

Explanations

lists or examples outlined in a structured format

oai_token-act-pair · gpt-3.5-turbo

instances of self-reflection or examples that illustrate a point

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

etheless

-0.60

sec

-0.59

)))

-0.57

 sqor

-0.56

isine

-0.56

ascus

-0.54

VERTISEMENT

-0.53

clerosis

-0.53

]).

-0.52

])

-0.52

POSITIVE LOGITS

 vowel

0.52

 versus

0.52

 hypothetical

0.51

 Slate

0.49

 divided

0.47

 randomly

0.46

 compute

0.46

 perceptual

0.45

 subdiv

0.45

 subjective

0.45

Activations Density 2.289%

lists or examples outlined in a structured format

instances of self-reflection or examples that illustrate a point

No Comments

No Known Activations