INDEX

Explanations

verbs or phrases related to reacting or responding to something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "responding to"

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

wine

-0.74

©¶æ¥µ

-0.71

Scope

-0.71

sky

-0.71

oval

-0.69

urn

-0.69

grand

-0.68

gebra

-0.67

rek

-0.66

lli

-0.66

POSITIVE LOGITS

PsyNetMessage

0.78

 behalf

0.74

 denounce

0.69

 counteract

0.68

 affirm

0.67

 criticism

0.67

 defend

0.66

cue

0.66

 reinforce

0.65

 ARTICLE

0.65

Activations Density 0.084%

verbs or phrases related to reacting or responding to something

instances of the phrase "responding to"

No Comments

No Known Activations