INDEX

Explanations

instances of words related to degree or intensity

oai_token-act-pair · gpt-3.5-turbo

the word "slightly" and its variations, indicating slight differences or nuances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yers

-0.77

velt

-0.75

 Aviv

-0.74

iture

-0.73

itures

-0.72

elsen

-0.71

ravings

-0.70

uments

-0.70

criptions

-0.68

 Parenthood

-0.68

POSITIVE LOGITS

 eccentric

0.81

 overlap

0.79

 inconven

0.79

 overlapping

0.77

 offset

0.76

 tang

0.76

 altered

0.76

 incl

0.75

 tilted

0.74

 inclined

0.72

Activations Density 0.030%

instances of words related to degree or intensity

the word "slightly" and its variations, indicating slight differences or nuances

No Comments

No Known Activations