INDEX

Explanations

ambiguity or uncertainty in statements

oai_token-act-pair · gpt-3.5-turbo

statements regarding uncertainty or lack of clarity

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

ython

-0.76

ctions

-0.72

atra

-0.72

itton

-0.68

acca

-0.67

pez

-0.67

%]

-0.67

bats

-0.66

ptin

-0.66

pour

-0.65

POSITIVE LOGITS

 anymore

1.04

nor

0.85

yet

0.81

 specifics

0.79

yet

0.75

TBD

0.71

 anything

0.71

 explan

0.67

 details

0.65

 conclusive

0.65

Activations Density 0.087%

ambiguity or uncertainty in statements

statements regarding uncertainty or lack of clarity

No Comments

No Known Activations