INDEX

Explanations

phrases or clauses indicating a subsequent action or event

oai_token-act-pair · gpt-3.5-turbo

references to subsequent events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Pwr

-0.74

mad

-0.71

lua

-0.67

ignment

-0.67

Ble

-0.66

hab

-0.66

 Mand

-0.65

THING

-0.64

rament

-0.64

ahead

-0.63

POSITIVE LOGITS

 regretted

0.96

 deleted

0.86

ally

0.81

 clarified

0.76

 recons

0.75

 discovered

0.75

 apologized

0.74

onymous

0.74

 reapp

0.73

 succumbed

0.73

Activations Density 0.037%

phrases or clauses indicating a subsequent action or event

references to subsequent events or actions

No Comments

No Known Activations