INDEX

Explanations

phrases expressing positive emotions or appreciation

oai_token-act-pair · gpt-3.5-turbo

expressions related to hearing or listening

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

itored

-0.73

Downloadha

-0.72

soDeliveryDate

-0.70

ailability

-0.68

 containment

-0.68

 tiss

-0.63

uminati

-0.61

 favoring

-0.61

 watershed

-0.61

 respectively

-0.60

POSITIVE LOGITS

ophob

0.73

enance

0.72

inen

0.68

\">

0.68

enos

0.68

agos

0.67

yles

0.66

dule

0.65

 RELEASE

0.65

borgh

0.64

Activations Density 0.261%

phrases expressing positive emotions or appreciation

expressions related to hearing or listening

No Comments

No Known Activations