INDEX

Explanations

words related to actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

action-driven words or verbs that imply struggle or persistence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

sonian

-0.70

 identification

-0.69

 clar

-0.66

 confirming

-0.64

 reversing

-0.62

 consequential

-0.61

 Samar

-0.60

 confirmation

-0.58

 unlocking

-0.57

 Identification

-0.57

POSITIVE LOGITS

rouse

1.03

igrated

0.97

igrate

0.96

ulate

0.93

raid

0.89

sed

0.88

semble

0.87

pose

0.86

ulates

0.85

have

0.85

Activations Density 0.155%

words related to actions or behaviors

action-driven words or verbs that imply struggle or persistence

No Comments

No Known Activations