INDEX

Explanations

future predictions or likelihoods

oai_token-act-pair · gpt-3.5-turbo

phrases expressing probability or likelihood

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

uctor

-0.66

 Curious

-0.64

 Tracks

-0.61

 Creator

-0.61

 Concept

-0.60

urat

-0.58

Que

-0.57

 Loop

-0.56

plates

-0.56

 Collector

-0.56

POSITIVE LOGITS

be

0.90

 settle

0.88

 suffice

0.81

 appreciate

0.80

 rely

0.79

 come

0.77

 raise

0.74

 translate

0.74

 reside

0.74

 recognize

0.73

Activations Density 0.038%

future predictions or likelihoods

phrases expressing probability or likelihood

No Comments

No Known Activations