INDEX

Explanations

verbs and nouns related to making requests, expressing opinions, and providing explanations in written form

oai_token-act-pair · gpt-3.5-turbo

verbs that indicate communication or requests

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

ktop

-0.82

nexus

-0.71

uld

-0.71

eka

-0.68

pedia

-0.68

idious

-0.67

nery

-0.66

utz

-0.66

nesia

-0.66

hound

-0.66

POSITIVE LOGITS

 conformity

0.67

tons

0.64

BUS

0.63

 signatures

0.62

INGTON

0.61

 alcoholic

0.60

 underage

0.60

 spirits

0.58

helps

0.58

 behalf

0.58

Activations Density 0.153%

verbs and nouns related to making requests, expressing opinions, and providing explanations in written form

verbs that indicate communication or requests

No Comments

No Known Activations